Relevance

How can we generate high-quality relevance annotations at scale without the cost and delays of human labeling? Relevance annotations are the backbone of search ranking systems which is needed for training data preparation, NDCG evaluation, and root cause analysis. However, human annotation is slow and off-the-shelf LLMs suffer from accuracy on domain-specific tasks. We propose a calibrated model cascade, a systematic approach for cost-efficient offline relevance annotation by routing queries through progressively larger fine-tuned classifiers. Our central insight is that accuracy and cost are orthogonal optimizations: domain-specific fine-tuning drives accuracy, cascading drives cost, and per-class isotonic calibration adds a small but reliable gain on top. Our contribution is threefold: (a) we decompose the gains and show that fine-tuning contributes 20 accuracy points while cascading is approximately accuracy-neutral but halves compute cost, (b) we introduce per-class isotonic calibration as one component of the cascade, contributing a small but statistically significant gain (+0.6 points over the strongest calibration baseline), and (c) we validate the system in production across six offline use cases, processing 150M+ annotations and enabling faster experimentation cycles. Our work is a building block for scalable, high-quality offline annotation pipelines in search and advertising systems.

Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generalization. While existing studies pursue this generalization-specialization trade-off with additional regularizations or constraints, we argue that they overlook the deviation of representations beyond the fine-tuning data distribution, resulting in suboptimal adaptation effects. We believe such deviation is inherited from the inconsistency between the fine-tuning and evaluation objectives, where model optimization is restricted to the known training distribution but evaluated on unseen ones. In this paper, we introduce \emph{TACO}, a simple yet effective framework to mitigate the potential negative effects induced by this inconsistency. Our key insight is that adaptation should preserve OOD-relevant alignment beyond the training distribution. To this end, we propose \emph{Relative Structure Distillation}, which regularizes the relative geometry of the representation space and suppresses harmful alignment shift during training. We further decouple the representation space from the optimization space with a lightweight specialization projection, allowing task-specific adaptation without directly overspecializing the representations used at test time. \emph{TACO} establishes state-of-the-art performance on diverse benchmarks under cross-dataset and base-to-novel settings. Code will be released at https://github.com/ZMHH-H/TACO.

Prior research on memory mechanism in RAG-based conversational system has emphasized how memory is stored and retrieved. However, far less is known about how memories with different functional roles influence response quality. Specifically, how they shape an agent's responses under varying conversational contexts and whether they lead to substantively different response behaviors. Existing evaluations in conversational system are also largely reference-based, insufficiently capturing the nuances in responses that may address users' preferences differently. In this work, we probe the impact of different memory types in shaping agents' responses. We present a fine-grained taxonomy of conversational memory, classify retrieved memories into different role types, and design a user-centric evaluation framework that simulates user perspectives. Through comparative experiments on long-term datasets and frontier LLMs, our analysis reveal many differentiated effects of memories: e.g., clarifying memory improves responses' factual accuracy and constraint awareness, making them more correct and personalized; irrelevant memory reduces topic relevance and degrades constraint awareness. Despite the power of frontier LLMs, these findings shed light on how different memory types can be leveraged to produce more personalized responses and inspire further research in this direction.

As retrieval systems scale, effective and efficient reranking becomes increasingly important. However, most existing encoder- and decoder-based rerankers jointly process every query--passage pair, tightly coupling their online computation and limiting deployment efficiency and flexibility. We present KaLM-Reranker-V1, a fast but not late-interaction FBNL reranker that decouples query and passage computation while retaining expressive relevance modeling. Built on an encoder--decoder architecture, KaLM-Reranker-V1 pre-encodes passages using Matryoshka embedding pooling, while its decoder models system and user instructions together with query intent; cross-attention then captures fine-grained relevance between the resulting query context and passage representations. Together, these designs offer four key advantages: (i) efficiency from offline passage encoding, (ii) expressiveness from cross-attention, (iii) compactness from Matryoshka embedding pooling, and (iv) test-time compute through an adjustable compute budget. We instantiate KaLM-Reranker-V1 in three sizes, Nano, Small, and Large, with 0.27B, 1B, and 4B activated parameters, respectively. Extensive experiments on BEIR, MIRACL, and LMEB demonstrate strong reranking performance with superior efficiency. On BEIR and MIRACL, our models achieve competitive performance in multi-domain and multilingual reranking, on par with strong industrial rerankers such as the Qwen3/BGE-Reranker series. On LMEB-Dialogue, a compact embedding model paired with our Nano reranker, which has only 0.27B activated parameters, remains competitive with 7--12B embedding models. Data and models are available at https://huggingface.co/collections/KaLM-Embedding/lychee-kalm-reranker-and-jev.

Automated test generation for telecom software systems and networks has advanced significantly with the adoption of machine learning and rule-based approaches. However, most existing solutions generate static test suites against a snapshot of the system; as code, configurations, topologies, and key performance indicators (KPIs) evolve, these tests quickly become outdated or misaligned with the live system. There is currently no widely adopted solution that continuously detects fine-grained changes and selectively adapts only the affected tests without regenerating entire test suites. This paper presents a context-aware generative AI framework for automated telecom test script generation that treats testing as a continuously adapting process driven by the current state of the system rather than a static artifact. The central contribution is delta-conditioned test generation over a live knowledge graph: our approach employs a continuously updated knowledge graph (KG) as a single source of truth, a delta engine for fine-grained change detection, and a KG-guided generative AI agent, operating via the Model Context Protocol (MCP), to create, update, or retire test cases automatically. We further integrate Retrieval-Augmented Generation (RAG) to enrich reasoning with telecom-domain knowledge and historical artifacts. We demonstrate applicability across software-system and telecom-network use cases, including a Python-based KPI monitoring application managed in GitLab, and show how the framework reduces manual effort, improves test relevance, and accelerates test cycles.

Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an eviction policy drops a task-critical detail, for example an access token issued at login or a path the next call needs, the action fails. We present LRE (Learned Relevance Eviction), a kilobyte-scale, CPU-only, language-model-free scorer that learns which units of history are task-critical and keeps them by verbatim extraction. Under a matched-budget comparison, in our experiment, no baseline dominates LRE on the accuracy-cost plane. On agents, LRE recovers 93% of the aggregate accuracy of keeping the entire history (41.1 vs. 44.0) and exceeds it by 27% on the simplest tasks, while requiring zero compressor calls and cutting the worst-case peak prompt by 52%. A controlled study trace shows LRE completes tasks where the others loop, finishing one such task in 37% fewer calls than keeping everything and solving 14 tasks where no other run policy does. On conversational memory, LRE outranks dense and token-pruning encoders at zero neural cost while being 295-1569x smaller in size. In downstream evaluation, LRE gives the best budgeted answer quality on LoCoMo reading 68% fewer tokens. Its supervision can also be annotation-free: training only on the system's own behavior recovers 95% of the supervised scorer's effectiveness. We argue that, because memory eviction in LLM agents is a fidelity problem, it requires a deployable proactive policy where the future query is unavailable and exact state is decisive, and that cheap learned relevance can be sufficient.

This paper presents Vortex, the multimodal video retrieval system developed by our team, FocusOnFun, for the Ho Chi Minh City AI Challenge 2025, designed to advance intelligent multimedia search and temporal reasoning. The system integrates adaptive keyframe extraction, multimodal metadata generation from vision-language and speech models, and a hybrid retrieval strategy that fuses CLIP and SigLIP2 embeddings through Reciprocal Rank Fusion to balance global and fine-grained semantics. To enhance interactivity, Vortex incorporates Rocchio-based relevance feedback and a multi-stage temporal search mechanism for sequential event alignment. Built on Milvus and Elasticsearch, the architecture enables scalable indexing and efficient retrieval. Evaluated in the official competition, our FocusOnFun team's system achieved a score of 79.6/88 (90.5%) in the Preliminary Round and was further evaluated in the Final Round, achieving an Excellent' overall performance with Outstanding' results in the question-answering (QA) task. This demonstrating the complementary strengths of CLIP and SigLIP2 and confirming the effectiveness of the hybrid retrieval approach. The system establishes a robust foundation for future research in intelligent, context-aware, and interactive video retrieval.

Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual tokens. While diversity maximization has become a dominant strategy for token reduction, existing methods rely on cosine-based normalized similarity that discards magnitude information, failing to faithfully approximate the original feature representation and leading to suboptimal performance, particularly on compositional multi-skill reasoning tasks. In this paper, we introduce SPARE, a subspace reconstruction method that reformulates token pruning as a column subset selection problem and explicitly minimizes reconstruction error. By iteratively selecting tokens with large projection residuals, SPARE performs reconstruction-driven pruning beyond angular diversity. Moreover, we reveal a counterintuitive anti-relevance phenomenon: tokens with lower image-text relevance score can better preserve contextual information. Based on this finding, we incorporate anti-relevance into SPARE as an additional selection criterion to promote context-aware token selection. Extensive experiments across multiple VLMs and benchmarks demonstrate that SPARE consistently achieves state-of-the-art performance, with strong gains on compositional tasks. When applied to LLaVA, SPARE removes up to 94% of visual tokens while retaining 95% of the baseline performance, all in a fully training-free manner.

Retrieval-Augmented Generation (RAG) is the prevailing architecture for grounding language model outputs in external evidence, yet its dominant evaluation paradigms and default configurations remain oriented toward factual question-answering. For interpretive disciplines such as historical studies, RAG embeds assumptions that conflict with scholarly practice. We introduce HistoRAG, a framework that translates historiographical principles into concrete architectural interventions. Separated retrieval and generation decouples source discovery from interpretation, temporal windowing enforces balanced source representation across the research period as a methodological requirement of historical inquiry, and LLM-as-judge evaluation makes relevance judgments transparent and contestable. We evaluate these interventions using SPIEGELragged, applied to 102,189 articles from Der Spiegel (1950-1979). Each intervention addresses a measurable deficiency in standard RAG: era-specific vocabulary retrieves zero chunks from the 1950s when using 1970s terminology, evidence of the temporal skew that motivates windowing; vector similarity and LLM-assessed relevance correlate only weakly (Spearman rho = 0.275), motivating post-retrieval evaluation; and keyword-based and semantic retrieval surface largely disjoint source pools, motivating an architecture in which both operate as complementary retrieval layers under a shared LLM evaluation filter. We also introduce the concept of Zwischentexte (intermediate texts that function as interpretive proposals rather than findings) as a framework for responsible integration of LLM-generated text into scholarly practice. The architecture offers a model for how domain-specific epistemological commitments can be translated into RAG design decisions, and may transfer to other interpretive disciplines working with large corpora.

Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregation. Its structured, verifiable workflow makes it an ideal substrate for evaluating systematic scientific reasoning, yet existing benchmarks lack ground truth across the full retrieval-screening-synthesis pipeline. We introduce MetaSyn, a dataset of 442 expert-curated meta-analyses from Nature Portfolio journals. Each entry pairs a research question with PI/ECO criteria, a retrieval corpus of 140k PubMed articles, verified positive studies, hard negatives that are topically similar but PI/ECO-ineligible, and complete search strategies and date bounds. Benchmarking twelve pipeline configurations (nine RAG variants and a protocol-driven agent) reveals a critical screening bottleneck: despite a retrieval ceiling of 90.9% recall at K=200, no system recovers more than 52.7% of ground-truth included literature. Current LLMs fail to reliably separate eligible studies from PI/ECO-failing distractors in pools of comparable topical relevance. Stage-attributed metrics capture where systems succeed and fail; a single end-to-end score does not.

Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval. The benefits reported for these methods come almost exclusively from homogeneous corpora, predominantly Wikipedia prose. Whether they hold on the mixed-format collections common in practice, where code, markdown, tables, scientific PDFs, and prose are interleaved within one corpus, has not been measured. To study this directly, we build \textbf{HetDocQA}, a heterogeneous benchmark with \emph{chunker-agnostic} span-overlap relevance labels and collection-disjoint splits, and pair it with MuSiQue and QASPER as homogeneous controls. We evaluate eight methods on a shared backbone, with bootstrap confidence intervals and multiple-comparison correction. A strong cross-encoder reranker accounts for most of the pipeline's quality; beyond it, only two methods yield reliable gains: query expansion and SSCC. SSCC, a per-source calibrated corrector introduced here, sets a separate acceptance threshold for each score source and helps only on heterogeneous data. The remaining reranking and pool-expansion methods in common use, among them hierarchical summarization, graph expansion, routing, and rank fusion, give no reliable gain once that reranker is present.

Entity-aware document retrieval uses query-associated entities as ranking signals, assuming that semantically relevant entities are also useful retrieval signals. We show this assumption is insufficient- and explain why. Unlike terms, which are ground-truth observations, entity links are hypotheses produced by an imperfect linker: an entity can be topically central yet provide no discriminative signal if the linker fires indiscriminately across relevant and non-relevant documents. We formalize this as a distinction between Conceptual Entity Relevance (CER)- whether an entity is topically related to a query- and Observable Entity Relevance (OER)- whether its observed presence in a collection discriminates relevant from non-relevant documents. Across four collections and annotation sources including human entity judgments, CER and OER exhibit near-chance agreement ($κ\approx 0$), while OER operationalizations agree substantially ($κ\approx 0.5$), confirming CER as the systematic outlier. CER-based supervision selects topically plausible but weakly discriminative entities, pruning fewer than 4% of non-relevant documents on some collections. Aligning supervision with OER improves non-relevant pruning by up to 10x and open-world MAP by 0.051 over BM25. Our findings motivate a shift from conceptual to observable notions of entity relevance in entity-aware retrieval.

LLM-based query expansion improves retrieval by enriching the original query with additional context. Yet most methods remain generation-driven, producing plausible pseudo-documents or expansions without checking how the target corpus responds. This can introduce retrieval drift, amplify misleading vocabulary, or miss terms that distinguish relevant from non-relevant documents. We argue that effective expansion requires retrieval-grounded feedback, not just single-pass generation or unverified iteration. We introduce ADORE (ADapt, Observe, Relevance Evaluate), an iterative framework that turns retrieval outcomes into feedback for the next expansion. At each round, an LLM generates pseudo-passages, a retriever exposes the corpus response, and a relevance assessor evaluates retrieved documents against the original query. These judgments identify what to reinforce, what remains undercovered, and what to suppress. Across TREC Deep Learning, BEIR, and BRIGHT, ADORE consistently outperforms strong query expansion baselines with notable improvements across nearly all evaluation settings, improving average nDCG@10 by 24.5% over BM25 and 3.6% over the strongest prior query expansion method on BEIR, and by 122.9% over BM25 and 9.2% over the best query expansion baseline on BRIGHT. Our code and data are publicly available.

Maritime accident adjudication reports contain critical tribunal findings for root cause analysis (RCA), yet retrieving relevant precedents and drafting consistent reports from decades of records remains labor-intensive. This paper proposes a multi-field hybrid retrieval-augmented generation (RAG) framework for automated maritime RCA, utilizing a comprehensive dataset of 13,329 Korea Maritime Safety Tribunal (KMST) reports (1971-2025). We transform raw adjudications into a structured knowledge base of "incident cards", indexing three distinct fields-Summary, Causes, and Disposition-alongside a hierarchical L1/L2 cause taxonomy. Our retrieval strategy employs a field-aware hybrid approach, fusing sparse and dense rankings via Reciprocal Rank Fusion (RRF). Given the lack of large-scale expert relevance labels, we evaluate retrieval performance using ceiling-normalized recall and nDCG based on a metadata-derived proxy relevance score. Experimental results demonstrate that our proposed retrieval significantly outperforms baseline methods, improving NormRecall@100 from 0.18 to 0.55. Furthermore, grounding the generator on the retrieved precedents enhances RCA generation quality over an LLM-only baseline, increasing the LLM-as-a-judge score from 3.34 to 3.72. These findings suggest that field-aware RAG can substantially streamline maritime safety investigation workflows by enabling faster precedent search and more consistent, evidence-based RCA drafting.

We propose a robust feature-weighted jump model for time-dependent clustering. A penalty is used to encourage smoothness of transitions over time, while robustness is achieved through the use of a Tukey's biweight loss function. An additional parameter controls the variability of feature weights across states, allowing the model to assign state-specific relevance to each feature. We illustrate in simulation how the method accurately recovers the true cluster sequence and reliably identifies relevant features, outperforming competing approaches, particularly in the presence of outliers. We conclude with two empirical applications, one on the number of conflict-related homicides in Kosovo in the period 1998-2000, and another on macroeconomic performance of twelve European countries in the period 1949-2024.

Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. Despite their promise, low-level controllers often become performance bottlenecks due to repeated execution failures. We argue that a key limitation is not only the lack of episodic memory, but also the decoupling of \textit{what-where-when} memory from \textit{which-why} reasoning. To address this, we propose \textbf{WISE} (Which-Why Informed Semantic Explorer), a long-horizon agent framework with an enhanced low-level controller equipped with a Causal Event Graph that augments episodic memory with explicit causal structure linking observations to task relevance. Unlike prior work such as MrSteve, which relies on feature similarity for retrieval, WISE enables robust recall under viewpoint changes and supports opportunistic task reordering through causal reasoning. Building on this memory, we propose an Opportunistic Task Scheduler that dynamically re-prioritizes subtasks when causally relevant opportunities are detected. We further equip WISE with a multi-scale progressive exploration strategy to provide spatially comprehensive observations for downstream reasoning. Experiments show that WISE largely improves task success and efficiency on long-horizon sparse tasks, particularly in settings requiring adaptive decision-making.

A social highlighter's most useful signal -- which passages a crowd of readers marks -- exists only for documents people have already read. Can the aggregate crowd salience of a document be predicted from its text before its marks accumulate? Prior work on this data found that zero-shot language models recover highlight locations worse than a trivial lead (position) baseline, so we ask whether a model trained on the highlight corpus can beat that baseline. Using a pre-registered ladder of models and a by-document cluster bootstrap, we find a small but robust edge: a logistic ranker over sentence embeddings and positional/contextual features beats the lead baseline by +0.044 average precision (95% CI [+0.029, +0.058]; clears a pre-registered margin delta=0.03 in 97% of resamples, and stable across pipeline re-runs). Two unsupervised extractive baselines (centroid, LexRank-style centrality) lose to lead, and the trained model beats them by +0.108, so the edge is not recovered by generic unsupervised proxies -- it reflects learning from real reader marks. In product terms, precision@3 rises from 0.25 to 0.39 (+55% relative) and the model beats lead on 69% of documents. An ablation attributes the edge to the raw embedding (+0.014) and training augmentation (+0.010), each with a positive CI. The edge is not a temporal-generalization failure, and we find no evidence that content drift or near-duplicate leakage explains it. A standardized regression shows the advantage is governed mainly by document popularity (lower popularity, larger edge) and by label reliability. It nearly vanishes only on the most popular content; there it is the lead baseline that strengthens, not the model that weakens. Because our evaluation conditions on documents that eventually accumulated readers, these results are a retrospective cold-start simulation.

Dense embedding retrieval compresses all relevance information into a single inner product, imposing a fundamental geometric limit -- the Voronoi Bottleneck -- on the number of query-document relevance patterns expressible at fixed embedding dimension (d). We make three contributions. (1) Unified capacity theory. We prove that Voronoi complexity and sign-rank are equivalent for top-1 retrieval, yielding tight dimension bounds and a computable diagnostic, the Capacity Utilization Score (CUS), that predicts per-query retrieval failure with AUC (> 0.8) without relevance labels. (2) Diagnosis. CUS identifies two capacity regimes -- moderate ((δ\gtrsim 1)), where density-aware training yields measurable gains, and vacuous ((δ\ll 1)), where it does not -- giving practitioners an a priori check before investing in retraining. (3) DART training. We introduce AT-DW-InfoNCE, an Adaptive-Temperature Density-Weighted contrastive objective with formally derived optimal weighting (α^* = 2.0). On a 100K-query synthetic product-search corpus with controlled relevance structure, DART improves +1.9 Recall@100 over a same-data InfoNCE baseline ((84.9 \pm 0.0) vs. (83.0 \pm 0.3); 8 seeds, (p < 0.001)), outperforming focal loss and temperature-schedule alternatives. DART requires zero inference-time overhead -- it is a drop-in training objective that improves any dual-encoder system.

Autonomous driving relies on computationally intensive perception pipelines to continuously detect and track objects in the surrounding environment. While some objects are key to plan safe and effective maneuvers, others may not be relevant and have no impact on the autonomous vehicle's driving decisions. Focusing on relevant objects allows a more efficient usage of available computational resources, reduces processing latencies, and limits the downstream propagation of perception noise. In this work, we propose a novel self-supervised approach based on counterfactual analysis to develop a relevance model - an AI-based tool that quantifies the relevance of objects for an autonomous vehicle. To demonstrate the potential of the proposed approach, we train a relevance model on a synthetic causal dataset generated in a selected urban scenario. Results show that the relevance model is able to accurately estimate the objects' relevance with millisecond-level latency, enabling real-time relevance estimation also in high-density scenarios. We also show that the relevance model can be used to build relevance heatmaps that offer valuable insights into the autonomous vehicle's driving policy and can be used to proactively inform perception and planning tasks. We openly release both the relevance model and the causal dataset.

Social highlighters let people mark passages that matter to them. We ask how much of an individual is recoverable from these naturalistic traces, using a co-readership identity control (the same document highlighted by many users) that holds document and topic fixed and asks whether a person's own history predicts their marks better than another reader's does. We separate generic salience (structure), crowd salience (what others marked), and personal salience (the individual residual). First, highlighting is social: which sentences you mark is predicted far better by the crowd than by structure or by a personal model, and even a well-estimated crowd, an information-privileged baseline that sees others' marks on the same document, beats a frontier LLM twin built from your other-document history; the within-document personal signal is at most a whisper (own-vs-other gap +0.017 by an embedding scorer, small but significant). Second, in sharp contrast, individuality lives in selection: asked which of the already-salient passages are yours, your own history is a strong, leakage-free predictor (gap +0.14). A topic decomposition shows this is largely stable thematic preference: it shrinks ~6-8x against a topically-matched peer, and a thin residual cannot be separated from finer topic. The non-obvious part is an asymmetry: under the same scorer the individual signal is ~6-8x weaker in salience than in selection. Methodologically, naive history-conditioning evaluations leak (the target's own marks enter the profile in ~42% of pairs, inflating personal scores by up to +0.15 AP) and small crowds overstate personalization; our results are leakage-free, use a dense crowd, and a model-matched control. Highlights carry a genuine individual signature, but a thin layer over a strong shared one, surfacing far more in which salient things a person selects than in what is salient.

Query recommendation in e-commerce search aims to proactively suggest queries that match users' potential interests. However, existing methods mainly optimize query-level relevance, while neglecting whether the retrieved products align with users' downstream preferences. This mismatch often leads to high query click through rates (CTR) but low product conversion rates (CVR). To bridge this gap, we propose QueryAgent-R1, a memory-augmented agentic framework that improves end-to-end alignment via chain-of-retrieval optimization. Our QueryAgent-R1 grounds query generation in real inventory retrieval, allowing the agent to validate and refine queries based on retrieved products. We also design a consistency reward in the agentic reinforcement learning (RL) process to jointly optimize query relevance and downstream engagement. In addition, we construct a memory abstraction module for efficient user profiling. To support offline evaluation, we construct two datasets based on both proprietary industrial data and public datasets, on which QueryAgent-R1 consistently outperforms strong baselines. Moreover, on a large scale production platform, QueryAgent-R1 improves Query CTR by 2.9% and guided CVR by 3.1% in online A/B tests.

Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet many existing memory systems organize information primarily by topical similarity and may ignore the order in which events occur. We introduce Segment Tree Memory, or SegTreeMem, a memory architecture that represents conversation history as a temporally ordered Segment Tree over utterances. SegTreeMem incrementally inserts new utterances through an online rightmost-frontier update rule, preserving chronological order while forming hierarchical memory segments. For retrieval, SegTreeMem propagates relevance scores through the tree to combine local semantic matching with hierarchical temporal context. Across three long-horizon memory benchmarks and two LLM backbones, SegTreeMem improves answer quality over flat retrieval, graph-structured memory, and tree-structured memory baselines. Additional temporal-order permutation analysis shows that the performance gain depends on preserving temporal order during memory construction, supporting the claim that temporal order is a key structure for agentic memory.

Despite rapid progress of continuous embeddings for e-commerce search relevance, a long-standing open problem is the difficulty in capturing fine-grained attribute distinctions. While discrete Semantic Identifiers (SIDs) have been widely adopted as a promising alternative, existing SID generation methods rely heavily on unsupervised quantization. In realistic scenarios, the lack of explicit supervision often makes it more difficult to dictate which items should share an SID, resulting in limited capability for query-dependent ranking. To address the issue of unsupervised SIDs, we propose to explicitly model discrete relevance features and develop a Discrete Semantic Identifier Relevance Model (DSIRM). Specifically, we present a query-bridged contrastive quantization approach on the item side, injecting query-item interaction supervision into Residual Quantization to actively learn relevance-aware semantic partitions. On the other hand, we explore generative LLMs on the query side to explicitly predict item SIDs from text, resolving tail queries and intent ambiguity. Hierarchical prefix matching between query and item SIDs yields discriminative features that perfectly complement dense signals. Extensive experimental results on Tmall's production data show that our proposed approach has achieved better results, improving offline AUC by +1.54%. Deployed via an efficient hybrid architecture, it achieves significant online lifts (+0.13% UCTR, +0.25% UCTCVR), proving its massive industrial value.

Retrieval-augmented generation systems for legal question answering typically retrieve passages based on semantic similarity and provide them to a language model, which then generates cited answers. Prior work assumes that highly ranked passages are most likely to be usefully cited by the model. Perturbation-based attribution methods, such as C-LIME, have been used exclusively for post-hoc explanation. However, on the AQuAECHR benchmark, semantic similarity does not correlate with passage attribution. Within a retriever's candidate pool, similarity-based ranking performs worse than random selection at surfacing gold citation paragraphs. To address this limitation, a lightweight cross-encoder is trained on continuous perturbation-based attribution scores to re-rank passages prior to generation. This approach is evaluated on the AQuAECHR benchmark, using two language models and five-fold cross-validation. The re-ranker substantially improves citation faithfulness and alignment with gold expert answers. Notably, two re-rankers trained independently on different models converge beyond their raw attribution agreement. This finding indicates that the cross-encoder reduces model-specific noise and produces a shared relevance signal that partially transfers across models, although same-model re-ranking remains more effective. These results demonstrate that perturbation-based attribution provides a practical, model-agnostic training signal for citation-aware retrieval.

Representation learning is often described as preserving the information in an input that is relevant for prediction. This work asks what relevance means for a fixed supervised decision problem. A representation is defined to be Bayes-sufficient for a joint distribution and loss if some prediction head can use it to implement a Bayes-optimal action rule. This makes the target information loss-dependent. In the almost-surely unique Bayes-action case, the relevant object is a Bayes quotient, which identifies inputs that require the same Bayes-optimal action. A representation is sufficient when it refines this quotient, and Bayes-minimal when it is informationally equivalent to it. The framework connects naturally to property elicitation: zero-one loss requires the Bayes class, squared loss the conditional mean, Brier loss the conditional probability in binary prediction, and log loss or strictly proper scoring rules the predictive distribution. Controlled finite experiments, learned neural bottleneck experiments, and a real-data iNaturalist taxonomic refinement experiment illustrate the distinction between sufficiency, minimality, and retained non-required information. For a fixed supervised problem, the distribution and the loss determine the Bayes action, the Bayes action determines the quotient, and the quotient determines the minimal information required for Bayes-optimal prediction.

Retrieval-augmented generative agents rely on retrieval for grounding, yet are typically evaluated on a query-by-query basis. This isolates interactions that are geometrically coupled in a shared embedding space. For example, we show that the high document density required to serve majority interests (e.g., generic "Crime" movies) can geometrically overcrowd the retrieval neighborhood of a semantically similar minority (e.g., "Film Noir"), effectively expelling minority content from top-$k$ results. We introduce a formal framework to analyze how such goal collisions in dense retrieval induce fundamental performance limits and emergent fairness issues inherent to spatial crowding. In our static analysis, we demonstrate that for a fixed embedding space, a phase transition occurs where minority user goals suffer a catastrophic collapse in performance as the density of majority goals increases. We then extend this to a dynamic model and derive a non-linear Fokker-Planck equation that governs the evolution of document embeddings as the agent updates them to maximize retrieval accuracy. Our analysis reveals that this local relevance objective triggers an emergent global mechanism that systematically marginalizes minority interests. We prove that such objectives drive the system to self-organize into a state that exclusively serves majority interests. These results provide a theoretical foundation for understanding a critical grounding failure mode in retrieval-augmented agents.

Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and this selection can favor certain document types over others. We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior: a query-independent signal encoded in their representation space as a side effect of training on annotated data. We estimate this prior by training simple classifiers on frozen document embeddings and evaluate three state-of-the-art retrievers across multiple IR benchmarks. We find that supervised neural retrievers encode relevance priors that generalize to unseen documents and are consistent across models. These priors create a findability gap: documents with lower prior are systematically harder to retrieve, even when genuinely relevant. This effect appears in supervised dense retrievers but is weaker and less consistent in BM25, and it persists under controlled matched-document comparisons. Using LLM-based explanations, we find that judged-relevant documents tend to be comprehensive, self-contained summaries of mainstream topics, while niche, fragmentary, or highly technical content is often left unjudged. Retrievers internalize this bias, ranking documents with these favored features higher than documents that lack them, independently of their actual relevance. Our findings expose a structural limitation of supervised retrieval: models trained on annotated data do not just learn relevance, but also the implicit document preferences in their training data.

We propose RCEM, a Robust Conversational search EMbedder that is additionally equipped with LLM's query reformulation capability without losing base model's generalization. Unlike prior conversational dense retrieval approaches that learn direct conversation-to-passage matching, RCEM aligns conversations, prepended by special token, to LLM-rewritten queries, while preserving the original embedding space. The unchanged embedding space automatically maps the rewritten-query to the relevant passages. As a result, RCEM (1) reduces overfitting by simplifying the alignment task from long passages to shorter rewritten queries, (2) eliminates the need for conversation-to-passage relevance labels for training, and (3) maintains its original embedding space that allows conversational queries against indexes built by original embedder without rebuilding them. Extensive experiments show that RCEM consistently outperforms prior approaches, achieving up to 30% improvement under distributional shift.

To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also examine its internal inference mechanisms to capture the complete picture. To explain the internal inference mechanisms of such models, it is essential to analyze the importance of latent representations for a given task. In this paper, we propose the \emph{normalized relevance measure} (NRM) framework -- a novel general explanation procedure that attributes relevance to \emph{arbitrary sets of neurons across layers of arbitrary architectures}. In the NRM framework, relevance of selected neurons is explicitly defined as a normalized signed measure, constructed using simple operations -- marginalization and conditioning based on additive and multiplicative laws -- in analogy to the probability measures. The normalization property further guarantees comparability across layers. The NRM framework subsumes existing propagation-based explanation algorithms by explicitly identifying the underlying quantity being computed. We demonstrate the utility of the framework in computer vision applications, where joint relevance analysis across multiple layers reveals key information flows in VGG16 networks. Overall, the NRM framework provides a general, mathematically grounded approach to understanding how modern NNs propagate information, offering a versatile and broadly applicable foundation for explainable artificial intelligence.

The same arguments often need to be evaluated under different external regimes. An agent with influence over the regime has a strategic lever that standard formalisms do not directly capture. We introduce context-dependent argumentation frameworks (CDAFs), an extension of Dung's theory in which a defeat function determines, per context, which attacks succeed. A perspective-labeled specialisation derives the defeat function from a relevance set $ρ$ and a priority $π$. The relevance set is the agent's action space. In a small worked example, the agent's target argument is rejected under every full-relevance injective priority, yet accepted under partial activations, one of which no VAF audience can mirror. We define the corresponding decision problem, ACTIVATION-MANIPULATION, and record baseline complexity bounds. Tight bounds and multi-agent variants are left open.

Scalable information retrieval testing needs corpora that are large enough to stress index construction, ranking latency, query routing, and evaluation tooling, yet human-judged test collections remain expensive and may be unavailable when documents are private or still under design. This paper introduces SPECTRA, a reproducible framework for generating synthetic text corpora and retrieval test collections through a separation of latent topical structure, surface text realization, metadata controls, query intent generation, and deterministic relevance oracles. The framework is intended as a diagnostic complement to Cranfield-style and TREC-style evaluation, not as a replacement for human assessment. A single-process Python prototype generated corpora up to 60,000 documents and 9.61 million tokens while preserving controllable long-tail vocabulary growth and producing graded relevance labels for 96 queries. In the local simulation study, generation remained close to linear at roughly 12K to 14K documents per second, estimated Zipf slopes stayed near 0.86 in absolute value, and increasing cross-topic distractor text reduced BM25 nDCG@10 from 1.00 at 2% distractors to 0.43 at 36% distractors. These results show that lightweight synthetic corpora can expose retrieval-system scaling and failure modes before costly collection construction begins.

Recommender systems may operate under multiple, competing objectives. For example, audience reach, cultural values, public service mandate, and operational constraints must be balanced in editorial decisions of public service media. Existing approaches relying on fixed combinations of objectives or Pareto-based optimisation do not adapt to changing priorities across situations. In this paper, we propose Contextual Scalarisation Thompson Sampler (CSTS), a multi-objective contextual bandit method that learns to weight objectives as a function of the observed context. We evaluate CSTS on real programming data from Radio Télévision Suisse, the Swiss national broadcaster, showing improved contextual relevance and better alignment with expert curation practices compared to fixed weight and standard contextual bandit approaches.

Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and ambiguous databases. Existing methods often treat schema linking as deterministic selection around a single SQL path, but complex questions may admit multiple valid realizations with different schema needs. We reframe schema linking as uncertainty-aware schema-need inference over multiple plausible SQL paths, where the system distinguishes required schema items from path-dependent uncertain ones and acquires evidence only where needed. We instantiate this reframing with EviLink, which combines multi-hypothesis schema grounding with uncertainty-guided evidence acquisition. Experiments on BIRD-Dev and Spider2-Snow show that this perspective improves the balance among schema completeness, schema relevance, and token cost. On Spider2-Snow, EviLink achieves 90.15% field-level strict recall rate, uses 123.30K average tokens, and improves downstream SQL generation under a fixed generator.

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines two axes: how retrieval is integrated into the agent pipeline and the properties of the retrieved content. Along the integration axis, we find that binding tool invocation and response generation in a single step amplifies harmful outputs. Along the content axis, we uncover the Safe Source Paradox: even oppositional or safety-oriented sources, such as pages containing warnings or risk disclaimers, can increase harmful compliance by an average of 25% compared to the no-retrieval baseline. Finally, we show that relevance acts as a shared activation condition for both vulnerabilities. Similar patterns appear on frontier closed models, and harmful compliance remains elevated under several representative pipeline interventions, with some agents also entering this regime under autonomous retrieval. Because relevance is also what makes retrieval useful, these results expose a safety-utility trade-off for retrieval-enabled agents. We introduce HarmURLBench, a benchmark containing 1,405 real-world URLs paired with 320 harmful behaviors to support future evaluations.

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in lexical judgments. We use human concreteness and imagery ratings because they span words with varying expected visual relevance, from abstract and low-imagery words to concrete and high-imagery words. We find that real-image contexts do not yield consistent gains and often hurt alignment with human ratings, most sharply when visual evidence is least relevant. Through probing and canonical correlation analysis, complemented by an attribution case study, we find that real-image contexts are associated with representational shifts and greater sensitivity to spurious visual cues, coinciding with weaker recoverability of the targeted lexical properties. We further show that instructing models to focus solely on textual content at inference time can reduce this degradation, with the clearest gains on these vulnerable subsets. Our findings suggest that current instruction-tuned VLMs need better calibration of when visual context should inform lexical judgments.

Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input or training data, hindering reliable deployment. In parallel, numerous uncertainty estimation (UE) methods have been proposed to quantify model confidence and are often implicitly treated as proxies for model failure. However, the relationship between uncertainty and hallucinations remains insufficiently characterized. We present a systematic empirical study of the association between uncertainty estimators and hallucinations in LLMs. Rather than assuming this association, we evaluate directly when and to what extent it holds. We consider a diverse set of uncertainty estimators, including information-theoretic, sampling-based, and reflexive estimators, and examine their behavior across hallucination settings. Our experiments cover both intrinsic hallucinations (violations of input faithfulness) and extrinsic hallucinations (unsupported claims relative to training data), using four complementary benchmarks, including RAGTruth and HalluLens. We find that the association is highly variable and often weak, depending on the hallucination type and the LLM under evaluation. These results challenge the use of uncertainty as a direct signal of hallucination and clarify when it provides actionable information.

The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression. We name and characterize this failure mode as action-grammar destruction -- the tokens carrying action semantics (identifiers, brackets, action verbs) are exactly those self-information ranks lowest, so a general-purpose compressor reliably removes them and the environment rejects the residual. The diagnosis points to step-granularity compression. We introduce AGORA, an inference-free step-level compressor combining a structural prompt parser, an always-keep floor for format- and recency-critical content, and a 125M-parameter relevance scorer trained on counterfactual next-action-change labels (~2ms/step, zero per-step LLM toll). Across the compared inference-free and LLM-based methods, AGORA is the only one retaining >= 75% uncompressed performance in 8 of 9 cells (with the lone exception at 73%); a four-way component ablation isolates the structural floor as the dominant quality lever and the learned scorer as the source of 1.0-11.5x adaptive end-to-end compression from a single fixed keep ratio.

Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations, but should change when perturbations alter legally material points. We formulate this requirement as a legal-relevance-sensitive evaluation problem: LLMs should only be sensitive to the legally relevant change. We introduce a unified evaluation suite covering should-change and should-not-change evaluation across judicial fairness, robustness, and statute-confusion scenarios. Our evaluation shows that existing legal LLMs are systematically sensitive to legally irrelevant variations and often fail to distinguish related legal elements and statutory rules. To mitigate these failures, we present LexGuard, an adversarial multi-agent framework grounded in formal reasoning. LexGuard formalizes statutes into executable constraints, uses adversarial agents to extract competing fact-statute arguments, and invokes SMT solvers to verify legal satisfaction and logical consistency. Experiments show that LexGuard improves legal reasoning reliability by reducing vulnerability to manipulative framing, improving disambiguation among similar statutes, limiting the influence of legally irrelevant attributes, and increasing consistency under benign reformulations. We show that legal trustworthiness requires not only accuracy, but calibrated sensitivity to legally material changes.

Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic feature-selection algorithm called minimum redundancy maximum relevance (mRMR), we can further improve upon these methods by selecting question subsets that will be maximally useful for prediction. Except in very data-poor settings, these approaches consistently achieve smaller prediction errors (in both MAE and RMSE), and greater ranking correlation between predicted and true scores (in both Spearman $ρ$ and Kendall $τ$) across a range of benchmarks using both binary and continuous metrics. Furthermore, mRMR subsampling is much faster than competitor methods (which often involve fitting probabilistic models or running clustering algorithms), and is more likely to select the same questions under different random seeds or training data splits. Tutorial code can be found at https://github.com/sambowyer/mrmr_eval .

AI answer engines generate answers from retrieved pages but cite only a few sources. This makes visibility depend not just on ranking, but on being cited. We study competitive Generative Engine Optimization (GEO): when two retrieved candidates compete, what makes one more likely to be cited first? We build a controlled two-document retrieval-augmented generation (RAG) testbed that injects exactly two candidate sources into the model context and measures which source is referenced by the first citation marker in the output. Across six LLMs we execute 252,000 trials, repeated paired comparisons under one factorial program over 18 content factors. In each trial the two sources differ in exactly one factor; we use brand anonymization and counterbalanced source order to separate content effects from position bias. Mixed-effects models show that topical relevance and list position are the biggest drivers of being cited first. Including explicit price information and a recent timestamp also helps consistently. Completeness and trust cues add smaller gains, while formatting-only edits have little impact. We release a reproducible evaluation protocol and a prioritized GEO checklist for practitioners, and we exercised it in an early internal pilot at Sprinklr, where teams reported positive qualitative feedback on workflow usability.

Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an implicit assumption from image-text retrieval: that visual semantics can be captured frame-by-frame. This assumption overlooks the temporal dynamics of egocentric videos. The EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge further raises the bar by providing soft-label relevance matrices rather than binary labels, demanding models that can resolve graded semantic correspondences across modalities. In this report, we present our solution, termed TempRet, to the CVPR 2026 EPIC-KITCHENS-100 MIR challenge. Our approach builds upon a CLIP-based dual-encoder backbone and introduces two key components to address the temporal and cross-modal challenges. First, a temporal transformer operates exclusively on the video side, modeling inter-frame dependencies through learnable positional encodings and multi-head self-attention over frame-level CLIP features. Second, a two-stage reranking pipeline first retrieves Top-K candidates via the dual-encoder, then refines their scores using a cross-encoder equipped with an Image-Text Matching (ITM) head. The entire system is trained with Symmetric Multi-Similarity Loss to exploit the soft-label relevance matrices provided by the challenge. Our method achieves 67.97% average mAP and 82.92% average nDCG on the EK-100 MIR benchmark, demonstrating the effectiveness of temporal modeling and cross-modal refinement for egocentric video retrieval.

Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, and robustness. Layer-wise relevance propagation for GNNs (GNN-LRP) evaluates the relevance of \emph{walks} to reveal important information flows in the network, and provides higher-order explanations, which have been shown to be superior to the lower-order, i.e., node-/edge-level, explanations. However, identifying relevant walks by GNN-LRP requires {\em exponential} computational complexity with respect to the network depth, which we will remedy in this paper. Specifically, we propose {\em polynomial-time} algorithms for finding top-$K$ relevant walks, which drastically reduces the computation and thus increases the applicability of GNN-LRP to large-scale problems. Our proposed algorithms are based on the \emph{max-product} algorithm -- a common tool for finding the maximum likelihood configurations in probabilistic graphical models -- and can find the most relevant walks exactly at the neuron level and approximately at the node level. Our experiments demonstrate the performance of our algorithms at scale and their utility across application domains, i.e., on epidemiology, molecular, and natural language benchmarks. We provide our codes under \href{https://github.com/xiong-ping/rel_walk_gnnlrp}{github.com/xiong-ping/rel\_walk\_gnnlrp}.

Joint Entity and Relation Extraction (JERE) is highly sensitive to training data quality, making data augmentation a natural way to improve generalization. However, existing augmentation methods often weaken entity relevance and disrupt semantic structure, limiting their effectiveness for JERE. In this paper, we propose \textbf{Structured Semantic Data Augmentation (SSDAU)}, a method designed to preserve triple-aware semantic structure during augmentation. SSDAU segments text by entity labels, captures semantic features through context-aware encoding, and restructures entity semantics to generate augmented data. To distinguish semantically similar entities, SSDAU combines contextualized embeddings with traditional similarity scores. To reduce topic inconsistency, we apply BERTopic-based filtering to remove irrelevant augmentations. We evaluate SSDAU on datasets with different annotation types and compare its performance on five representative JERE models against seven popular augmentation baselines. Experiments show that SSDAU generates semantically consistent data, is more robust to ambiguity than non-LLM methods (8.95% vs. 23.58% average relative F1 decrease), and significantly outperforms strong alternatives in most settings.

Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG) pipelines optimize for semantic similarity, which frequently surfaces passages that are topically related but lack decision utility, a problem we term the similarity-utility gap. We propose a two-phase non-parametric retrieval architecture that separates high-recall candidate retrieval from high-precision utility ranking. The first phase combines lexical and dense multilingual retrieval to construct a broad candidate pool. The second phase applies an adaptive retrieval controller that filters candidates using query intent and document structure signals, followed by an LLM-as-a-Judge utility scoring mechanism that ranks passages by analytical usefulness rather than semantic proximity. A context-aware extraction module preserves structural fidelity across narrative text and complex financial tables. The system is deployed entirely on-premise to satisfy enterprise data governance requirements. Evaluated on a multilingual corpus of proprietary financial documents with analyst-curated relevance labels, the system significantly outperforms naive retrieval baselines. In production deployment across more than 800 credit analysts, document review time was reduced from several hours to approximately three minutes, demonstrating the practical value of utility-aware RAG architectures for document-intensive decision-support workflows.

We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specific content of the context and depends only on its length. We prove that as context length increases, RoPE-based attention becomes unpredictable and loses two properties that are central to its effectiveness. First, it loses its locality bias: RoPE is no more likely to favor nearer positions than substantially farther ones. Second, it loses consistency in token relevance: a key vector that receives a higher attention score than an alternative at one position may receive a lower score at another. In both cases, the probability of failure approaches 0.5, no better than random guessing. We further prove that the attention score can remain unchanged when a key token is moved to a different position, or even replaced by a different token, indicating a failure to distinguish positions or tokens. Adjusting the RoPE base trades off distinguishing positions against distinguishing tokens but cannot preserve both at the same time. Increasing the RoPE base hyperparameter, a common practice in today's long-context models, helps distinguish different tokens, but inevitably sacrifices the ability to distinguish positions. Our empirical analysis shows that multi-head, multi-layer architectures are insufficient to overcome these limitations. Our findings suggest that fundamentally new mechanisms for encoding position and token order may be needed in future Transformer long-context language models.

LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at hand. Existing learned pruners compress this context with a single-objective sequence labeler, collapsing all facets of code relevance into one score and one transition matrix. We show that this formulation creates a modeling bottleneck: a single CRF transition prior must serve heterogeneous retention patterns, including contiguous semantic spans and sparse structural support lines. We propose LaMR (Latent Multi-Rubric), a structured pruning framework that decomposes code relevance into two interpretable quality dimensions, semantic evidence and dependency support, each modeled by a dedicated CRF with dimension-specific transition dynamics. A mixture-of-experts gating network dynamically weights the per-rubric emissions conditioned on the query, and a final CRF layer on the fused emissions produces the aggregate keep-or-prune decision. To supervise each dimension without additional annotation cost, we derive multi-rubric labels from the existing training corpus via AST-based program analysis, simultaneously denoising the teacher's binary labels. By effectively filtering distracting noise, LaMR frequently matches or even outperforms unpruned full-context baselines. Experiments on four benchmarks (SWE-Bench Verified, SWE-QA, LCC, LongCodeQA) show that LaMR wins 12 of 16 head-to-head multi-turn comparisons. It saves up to 31% more tokens on multi-turn agent tasks and improves Exact Match by up to +3.5 on single-turn tasks, while performance is frequently enhanced by denoising the context, and any remaining drops are marginal.

In search and recommendation systems, predictive models often suffer from temporal instability when certain input features introduce volatility in output scores. This instability can degrade model reliability and user experience especially in multi-stage systems where consistent predictions are critical for downstream decision making. We introduce Fortress, a general framework for enhancing model stability and accuracy by identifying and pruning features that contribute to inconsistent prediction scores over time. Fortress leverages historical snapshots temporally partitioned datasets capturing score fluctuations for the same entity across periods and follows a four-step process: (1) collect historical snapshots, (2) identify samples with unstable predictions, (3) isolate and remove instability-inducing features, and (4) retrain models using only stable features. While semantic features from LLMs and BERT-based models improve generalization, they often lack full query or entity coverage. Engagement-based features offer strong predictive power but tend to introduce temporal instability. Fortress mitigates this trade-off by suppressing the volatility of engagement signals while retaining their predictive value leading to more stable and accurate models. We validate Fortress on a query-to-app relevance model in a large-scale app marketplace. Offline experiments demonstrate notable improvements in prediction stability (measured by Coefficient of Variation) and classification performance (measured by PR-AUC).

Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant ones, which often leads to negative transfer. In this paper, we address this challenge by leveraging expert textual descriptions of the target domain, a resource that is often available but overlooked. We propose a probabilistic framework that translates these semantic descriptions into a choice model, namely a Language-Induced Prior (LIP), that learns the preferences from a pretrained Large Language Model (LLM). The LIP is then integrated into an Expectation-Maximization algorithm to identify source relevance. Methodologically, this framework is compatible with any parametric model where a likelihood is available. It allows the LIP to guide the selection of sources when target signals are weak, while gradually refining these choices as samples accumulate. Theoretically, we prove that the estimator roughly matches an oracle cold-start MSE under a correct prior, while remaining asymptotically consistent regardless of the quality of the LIP. Empirically, we validated the framework on a descriptive (Gaussian estimation), a predictive (C-MAPSS dataset), and a prescriptive task (MuJoCo hopper).

Multimodal Large Language Models (MLLMs) have facilitated Multimodal Summarization with Multimodal Output (MSMO), wherein systems generate concise textual summaries accompanied by salient visuals from multimodal sources. However, current MSMO evaluation remains fragmented: text quality, image-text alignment, and visual diversity are typically assessed in isolation using unimodal metrics, making it difficult to capture whether the modalities jointly support a faithful and useful summary. To address this gap, we introduce MM-Eval, a unified evaluation framework that integrates assessments of textual quality, cross-modal alignment, and visual diversity. MM-Eval comprises three components: (1) text quality, measured using OpenFActScore for factual consistency and G-Eval for coherence, fluency, and relevance; (2) image-text relevance, evaluated via an MLLM-as-a-judge approach; and (3) image-set diversity, quantified using Truncated CLIP Entropy. We calibrate MM-Eval through a learned aggregation model trained on the mLLM-EVAL news benchmark, aligning component contributions with human preferences. Our analysis reveals a text-dominant hierarchy in this setting, where factual consistency acts as a critical determinant of perceived overall quality, while visual relevance and diversity provide complementary signals. MM-Eval improves over heuristic aggregation baselines and provides an interpretable, reference-weak framework for comparative evaluation of multimodal summaries.

Adobe Express is expanding internationally, but the US has a disproportionately large content supply and interaction volume. Learning-to-rank (LTR) models trained primarily on behavioral feedback inherit this imbalance: templates popular in US are over-served in non-US locales. This cross-locale exposure bias suppresses local content discoverability and degrades ranking quality in growth locales. We show that click-only training suppresses semantically informative localization features. Adding vision-language model (VLM) graded relevance labels as auxiliary supervision alongside clicks improves semantic alignment but does not preserve local content visibility. We propose a multi-objective framework combining behavioral supervision, VLM-derived relevance signals, and locale-aware boosting. Across five locales, the resulting model improves relevance while restoring stable localization, demonstrating the importance of disentangling exposure from semantic supervision.

Graph Neural Networks (GNNs) excel at relational reasoning but face two persistent challenges: the lack of interpretable attribution for heterogeneous node types, and the computational overhead of message passing over large, noisy graphs. We propose the Hierarchical Attention-based Heterogeneous GNN (HA-HeteroGNN), a framework that addresses both issues through a unied explainability-to-pruning pipeline. A two-tier attention mechanism separates sensor-level and context-level computation across 16 node types and 18 edge types, producing per-node relevance scores via an attention-based GNN Explainer without requiring gradient backpropagation. These relevance scores then serve as a principled pruning criterion: removing nodes identied as consistently uninformative yields a 27% reduction in graph edges while simultaneously improving classication accuracy by 2.46.1% across all model variants, challenging the conventional assumption that pruning necessarily trades accuracy for eciency. Experiments on a 50,000-record synthetic dataset spanning 11 report categories demonstrate 97.5% cross-strategy explanation stability and domain consistent sensor attribution, with training-time reductions of up to 43.9% and real-time inference latency of approximately 5860 ms per sample.

Visual Document Retrieval (VDR) models mostly rely on late interaction architectures, in which documents are represented by a set of local patch embeddings and then matched against query tokens. While efficient, this architecture prioritizes local similarity over global layout structure of documents to estimate relevancy between documents and query. In practice, this leads to errors as relevance originates from layout structure of documents with heterogeneous layouts combining figures, tables, and text. We make document layout learnable without changing inference. We propose a multimodal encoder that augments local patch representations with a global layout embedding, trained via textual descriptions encoding document layout information. Across four ViDoRe-v2 datasets, our model improves over the strongest architecturally comparable ColPali/ColQwen baseline by +2.4 nDCG@5 and +2.3 MAP@5, with statistically significant per-dataset gains over ColQwen.

Channel importance in vision networks is usually summarized by a single score. That summary hides two different questions: how much a channel is related to the task, and whether its function can be supplied by same-layer peers when the channel is removed. We call the second property local replaceability. We introduce a two-axis view that separates these questions. The local axis measures input capture and peer overlap, while the target axis measures task information and target-excess information. Across ResNet-18, VGG-16, and MobileNetV2 trained on CIFAR-100, the two axes are weakly aligned, induce different channel groupings, and separate rapidly during training despite being strongly coupled at random initialization. A Gaussian linear analysis accounts for how this separation can arise through residualized gradient directions, and lesion plus peer-replacement experiments show that peer support refines removability beyond input capture and task relevance alone. Under the fixed FLOPs-matched pruning protocol, local-axis metrics are more reliable predictors of removability than target-axis metrics across the three CIFAR-100 backbones, with the same direction preserved in stress tests on CIFAR-10, Tiny-ImageNet, ImageNet-100, and a ConvNeXt-T/ImageNet-100 pilot. These findings identify an axis-level distinction rather than a universal ranking of pruning scores: local replaceability is a more reliable guide to removability than target relevance, while norm-based baselines remain competitive in architectures such as VGG-16. Relevance-based scores ask what a channel says about the task; pruning asks whether the network still needs that channel when its peers remain available.

Retrieval-Augmented Generation (RAG) depends on document ranking to provide useful evidence for generation, but conventional reranking methods mainly optimize query-document relevance rather than generation usefulness. A relevant document may still introduce noise, while a lower-ranked document may better reduce the generator's uncertainty. We propose CAR (Confidence-Aware Reranking), a query-guided, training-free, and plug-and-play reranking framework that uses generator confidence change as a document usefulness signal. CAR estimates confidence through the semantic consistency of multiple sampled answers under query-only and query-document conditions. Documents that significantly increase confidence are promoted, those that decrease confidence are demoted, and uncertain cases preserve the baseline order, while a query-level gate avoids unnecessary intervention on already confident queries. Experiments on four BEIR datasets show that CAR consistently improves NDCG@5 across sparse and dense retrievers, LLM-based and supervised rerankers, and four LLM backbones. Notably, CAR improves the YesNo reranker by 25.4 percent on average under Contriever retrieval, and its ranking gains strongly correlate with downstream generation F1 improvements, achieving Spearman rho = 0.964.

Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a single matching moment for each query. This assumption does not always hold in real-world scenarios, where queries may correspond to multiple or no moments. Thus, we formulate Generalized Moment Retrieval (GMR), a unified setting that requires retrieving the complete set of relevant moments or predicting an empty set. To enable systematic study of GMR, we introduce Soccer-GMR, a large-scale benchmark built on challenging soccer videos that reflect general GMR scenarios, with realistic negative and positive queries. The benchmark is constructed via a duration-flexible semi-automated pipeline with human verification, enabling scalable data generation while maintaining high annotation quality. We further design a unified evaluation protocol with complementary metrics tailored for null-set rejection, positive-query localization, and end-to-end GMR performance. Finally, we establish strong baselines across two modeling paradigms: a lightweight plug-and-play GMR adapter for discriminative VMR models, and a GMR-tailored GRPO reward for fine-tuning multimodal large language models (MLLMs). Extensive experiments show consistent gains across all metrics and expose key limitations of current methods, positioning GMR as a more realistic and challenging benchmark for video-language understanding.

Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and audio-language tasks. However, a critical challenge remains: these models often suffer from hallucinations, generating outputs that diverge from the provided perceptual inputs. This tendency stems from an inherent imbalance in modality utilization during inference, where the dominance of textual tokens undermines the potential of perceptual inputs. As a result, the model frequently resorts to textual language priors at the expense of grounded evidence. To tackle this issue, we propose Learning Inference-time Modality Enhancement (LIME), a training-free framework designed to bolster multimodal grounding by explicitly enhancing modality usage during decoding. LIME leverages Layer-wise Relevance Propagation (LRP) to quantify token-level contributions and defines a relevance-based objective that promotes increased reliance on perceptual inputs. This objective is enforced through inference-time updates to the model's key-value representations, without modifying model parameters or requiring additional training data. We evaluate LIME across multiple multimodal benchmarks in both vision and audio domains, demonstrating consistent reductions in hallucinations and enhanced grounding while preserving generation quality. Further analysis shows that LIME increases modality contribution and produces more localized and semantically aligned relevance patterns.

The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM's reasoning ability through Verbal Annotations, analytic narratives that explicitly articulate the logical connection between a search query and retrieved contexts. Our empirical investigation reveals the potential of Verbal Annotations to substantially enhance the LLM's ability to generate accurate, contextually-grounded responses. Motivated by this finding, we introduce Verbal-R3, a novel agentic RAG framework that consists of a Generator and a Verbal Reranker. The Generator performs iterative retrieval and reasoning, while the Verbal Reranker returns relevance scores and Verbal Annotations to guide the reasoning and answering process of the Generator. The inference process of Verbal-R3 is further refined through relevance-guided test-time scaling, which efficiently allocates test-time compute for effective trajectory expansion. Verbal-R3 achieves state-of-the-art performance on complex Question Answering benchmarks, validating the effectiveness of the proposed framework.

The Hypencoder, proposed by Killingback et al., is a retrieval framework that replaces the fixed inner-product scoring function used in standard bi-encoders with a query-specific neural network (the $q$-net), whose weights are generated by a hypernetwork from the contextualized query embeddings. This design enables more expressive relevance estimation while preserving independent query and document encoding. In this work, we conduct a reproducibility study of the Hypencoder and extend the original analysis in three directions. Our reproduction confirms that the Hypencoder outperforms a similarly trained bi-encoder baseline on in-domain and out-of-domain benchmarks, and that the proposed efficient search algorithm substantially reduces query latency with minimal performance loss. On hard retrieval tasks, we find partial support: the Hypencoder outperforms the baseline on DL-Hard and FollowIR, but not on TREC TOT, where checkpoint incompatibility and fine-tuning sensitivity complicate full verification. Beyond reproduction, we investigate three extensions: (i)~integrating alternative pre-trained encoders into the Hypencoder framework, where we find that performance gains depend on the encoder and fine-tuning strategy; (ii)~comparing query latency against a Faiss-based bi-encoder pipeline, revealing that standard bi-encoder retrieval remains faster under both exhaustive and efficient search settings; and (iii)~evaluating adversarial robustness, where we find that the $q$-net's non-linear scoring does not provide a consistent robustness disadvantage over inner-product scoring. Our code is publicly available at https://github.com/arneeichholtz/Hypencoder-reprod.

Large Language Models (LLMs) have recently been explored as fine-grained zero-shot re-rankers by leveraging attention signals to estimate document relevance. However, existing methods either aggregate attention signals across all heads or rely on a statically selected subset identified by heuristic rules. This solution can be suboptimal because the informative heads can vary across queries or domains. Moreover, naively combining multiple heads can degrade performance due to redundancy or conflicting ranking signals. In this paper, we propose a query-dependent head selection method, RouteHead, for attention-based re-ranking with LLMs. Specifically, we learn a lightweight router that can map each query to an optimal head set, and relevance scores are computed by aggregating attention signals only from these heads. Since query-to-head optimal labels are unavailable, we first construct pseudo labels via an offline search. The router represents each head with a learnable embedding and represents each query using an embedding extracted from the hidden states of the frozen LLM. Then it is trained on the pseudo labels with a sparsity regularizer. Experiments on diverse benchmarks and multiple LLM backbones show that the proposed method consistently outperforms strong baselines.

Depression places substantial pressure on mental health services, and many people describe their experiences outside clinical settings in high-volume user-generated text (e.g., online forums and social media). Automatically identifying clinical symptom evidence in such text can therefore complement limited clinical capacity and scale to large populations. We address this need through sentence-level classification of 21 depression symptoms from the BDI-II questionnaire, using BDI-Sen, a dataset annotated for symptom relevance. This task is fine-grained and highly imbalanced, and we find that common LLM approaches (zero-shot, in-context learning, and fine-tuning) struggle to apply consistent relevance criteria for most symptoms. We propose Symptom Induction (SI), a novel approach which compresses labeled examples into short, interpretable guidelines that specify what counts as evidence for each symptom and uses these guidelines to condition classification. Across four LLM families and eight models, SI achieves the best overall weighted F1 on BDI-Sen, with especially large gains for infrequent symptoms. Cross-domain evaluation on an external dataset further shows that induced guidelines generalize across other diseases shared symptomatology (bipolar and eating disorders).