Dense Retrieval

Ask about this topic

Overview

Dense retrieval encodes queries and candidates as vectors, then uses nearest-neighbor search to find relevant results, often where exact keyword matching is inadequate. Common approaches include dual encoders trained with contrastive learning and hard negatives, late-interaction models that match token-level representations, and hybrid systems that combine dense scores with lexical retrieval or reranking. Researchers evaluate these methods on benchmarks such as BEIR and domain-specific tests, while also developing compact indexes, multilingual and specialized retrievers, and retrieval for long documents or agent tasks. A central tension is that stronger models and richer representations can improve difficult or compositional search but cost more to train and serve; generalization, robustness, fairness, and reliable constraint handling remain open challenges.

Latest papers

CardsList

152 papers17 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

May 31, 2026

Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG

Ensuring factuality and interpretability in RAG remains an open and urgent problem. We introduce Contrastive Evidence Rationale Attention (CERA), the first retrieval framework to employ subjectivity-based hard negative selection and inject an evidential inductive bias into contrastive learning through an auxiliary attention alignment loss. CERA fine-tunes a dense retriever using two training objectives: triplet-based contrastive learning and interpretable attention alignment, which supervises CLS-to-token attention using a part-of-speech-weighted masking distribution over human-annotated factual rationales as evidence signals. Experiments on a large corpus of clinical trial reports demonstrate that the subjectivity-based hard negative selection substantially improves retrieval effectiveness compared to both Contriever and hard negative selection baselines. Furthermore, rationale alignment improves faithfulness while maintaining competitive retrieval performance, supporting the hypothesis that attention can serve as a more faithful explanation of model behavior when guided by human rationales. Moving beyond topical similarity, CERA enables the retriever to identify the specific tokens that constitute supporting evidence, promoting more interpretable evidence selection in RAG systems.

Francielle Vargas, João Robiatti, Diego Alves +6

University of Chile · São Paulo State University · Saarland University +4

Retrieval-Augmented GenerationEvidence SelectionEvidence RetrievalDense Retrieval
AskPDF
May 31, 2026

When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval

Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriever score rather than diagnostic value, and increasingly contaminated by false positives as the retriever improves. LLM-based synthesis offers a principled alternative, where negatives that are unconstrained, targeted, and free from false positive risk. But we show that naively incorporating generated negatives into contrastive learning often degrades retrieval performance. We identify and formalize the root cause as a generative-discriminative gap: LLM generation optimizes for fluent, plausible text, while contrastive learning demands strategic violations of relevance at the decision boundary. Our analysis reveals two compounding failure modes: discriminative-agnostic generation, where the LLM lacks an explicit model of query information needs and defaults to generic or topic-drifted text that provides no contrastive signal; and source-dependent shortcuts, where distributional artifacts enable the model to distinguish negatives by origin rather than relevance, causing gradient drift that actively corrupts optimization. To close this gap, we propose CausalNeg consisting of two main modules: (1) CoT-guided counterfactual perturbation for data construction: decomposes why a document satisfies a query into explicit information requirements, then surgically violates individual requirements to construct negatives with controlled, interpretable hardness. (2) Query-view entropy maximization during training: disperses generated negatives across the similarity spectrum, minimizing the mutual information between source identity and similarity scores to suppress shortcut exploitation. We make our code publicly available at https://github.com/mzhangzhicheng/CausalNeg.

Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9

Shenzhen International Graduate School, Tsinghua University Shenzhen, China · Huawei Technologies Co., Ltd. Shenzhen, China · City University of Hong Kong Hong Kong SAR, China +4

Contrastive LearningHard Negative MiningSynthetic Data GenerationDense Retrieval
AskPDF
May 31, 2026

Test-Time Training for Zero-Resource Dense Retrieval Reranking

Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamental dilemma: cross-encoders deliver strong reranking quality but require costly supervised training and incur high latency, while unsupervised BM25 reranking consistently degrades dense retrieval performance on most of BEIR benchmarks. We propose DART (Dense Adaptive Reranking at Test-time), which resolves this dilemma by adapting the scoring function at inference time. For each query, the top-ranked documents serve as pseudo-positive examples and the bottom-ranked as pseudo-negative examples, providing noisy but readily available supervision to adapt a bilinear scoring matrix WW via a small number of gradient updates. We further introduce a confidence-weighted margin loss and a cross-query momentum buffer that warm-starts adaptation across queries. On six BEIR benchmarks, DART achieves a mean per-dataset relative NDCG@10 gain of +2.1% over the dense retrieval baseline with under 10ms additional latency per query, demonstrating a powerful capability for zero-shot performance enhancement and cross-domain generalization.

Shiyan Liu, Yichen Li

Huazhong University of Science and Technology · ByteDance

Zero-Shot LearningLearning to RankTest-Time TrainingDense Retrieval
AskPDF
May 28, 2026

Xetrieval: Explaining Dense Retrieval through Feature Elicitation

Dense retrieval enables effective semantic matching, yet the semantic factors underlying its relevance scores remain opaque. Sparse autoencoders (SAEs) support feature-level explanations by decomposing dense embeddings into sparse semantic features. However, the document semantics underlying a retriever's relevance scores may not be sufficiently explicit in the embeddings to be recovered as interpretable SAE features. We introduce Xetrieval, a framework for explaining dense retrieval through feature elicitation. Feature Elicitors make retrieval-relevant aspects of document meaning more explicit through auxiliary views, facilitating their identification as interpretable SAE features. A shared sparse dictionary learns from these varied representations to express query--document relations through describable features. We assess their influence on relevance scores through interventions on the original document embeddings. Experiments show that Xetrieval yields more interpretable features than an SAE baseline and identifies feature sets with a stronger influence on the retriever's scores. Task-level feature modulation further demonstrates more effective retrieval steering. These findings highlight the value of feature elicitation for relevance attribution and retrieval steering.

Zhixin Cai, Jun Bai, Yang Liu +7

School of Computer Science and Engineering, Beihang University · State Key Laboratory of General Artificial Intelligence, BIGAI

Text Embedding ModelsDense Retrieval
AskPDF
May 28, 2026

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies

We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can trivially be decomposed into retrieval-ready sparse features. When trained on frozen retrievers, Sparse Autoencoders without any retrieval-specific adjustments extract a latent vocabulary with approximately Zipfian collection statistics, directly suitable for classical sparse retrieval scoring via BM25. This approach enables sparse retrieval while requiring no learned expansion objective or sparse retrieval supervision whatsoever, and can be readily applied to any dense retriever. Latent Terms is able to match or outperform single-vector scoring methods from its own base model as well as comparable SPLADE variants. In addition, it substantially outperforms its base model on LIMIT, a task specifically designed to highlight the failures of single-vector retrieval. Overall, our results highlight that neural retrievers contain more expressive and indexable structure than their default scoring functions expose, but that other methods can nonetheless be leveraged.

Benjamin Clavié, Sean Lee, Aamir Shakir +1

Mixedbread AI · National Institute of Informatics (NII) · University of Tsukuba

Learned Sparse RetrievalInformation RetrievalDense Retrieval
AskPDF
May 28, 2026

CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval

Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog uses technical API vocabulary that no fixed encoder can bridge on its own. The two dominant training approaches, contrastive encoder fine-tuning and HyDE-style query expansion with a frozen LLM, address this problem from opposite ends and fail in complementary directions: the fine-tuned encoder excels when the query's surface form already matches the catalog but collapses when it does not, while zero-shot HyDE is more robust to underspecified queries yet generates catalog-unaware hypothetical descriptions that degrade retrieval when queries are well-formed. We introduce CoHyDE, an iterative procedure that trains the dense encoder and the LLM rewriter as a single co-evolving system: the encoder is retrained with InfoNCE on catalog-style hypothetical descriptions produced by the rewriter, and the rewriter is preference-aligned via DPO against the encoder's retrieval scores, with both sides warm-started on the tool catalog before the loop begins. On a ~10k tool subset of the ToolBench catalog, three rounds of CoHyDE improve over the strongest single-component baseline by +2.5 pp NDCG@5 on standard queries and +6.3 pp on held-out vague queries, with gains as large as +8 pp on the hardest vague tier. Ablations confirm that co-training is the key ingredient: using either component in isolation fails to match CoHyDE on both well-formed and vague queries, with losses of up to -8 pp on vague queries.

Vaishali Senthil, Ashutosh Hathidara, Sebastian Schreiber

SAP Labs

Tool-Augmented Language Model AgentsLLM Tool UseDense Retrieval
AskPDF
May 23, 2026

Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retrieval in LLM Multi-Agent Systems

[Abridged] - Spectral Retrieval is a plug-in re-ranking stage that interpolates between per-token MaxSim and mean-pool retrieval through a multi-scale sinc convolution over token embeddings. In standard dense retrieval each document is one mean-pooled vector; when relevance localises into a short subspan, the signal averages into noise. Spectral Retrieval reuses per-token embeddings from a late-interaction index and convolves them with a normalised sinc kernel at multiple scales. At L=1 the kernel acts as the identity, recovering per-token MaxSim; as L grows it approaches a uniform filter, recovering mean pooling. The maximum cosine over positions and scales yields a score provably no less informative than either endpoint. On a controlled synthetic benchmark with 1,000 documents and planted single-position spikes, mean-pool retrieval sits at chance (Recall@10 ~ 0.02) regardless of spike strength, while Spectral Retrieval reaches Recall@10 = 1.0 once the planted cosine exceeds the corpus-level token noise floor. On LIMIT-small with a frozen all-mpnet-base-v2 encoder, Spectral Retrieval lifts Recall@10 from 0.33 to 0.90, MRR from 0.22 to 0.79, and strict Success@10 from 0.12 to 0.84, without retraining. The method fits naturally into multi-agent LLM systems, where each agent benefits from a tighter, role-specific retrieval window over a shared corpus.

Andrea Morandi

Cisco Systems, Inc.

Late Interaction RetrievalMulti-Vector RetrievalDense Retrieval
AskPDF
May 22, 2026

HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval

In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper bounds on public benchmarks, their deployment in high-throughput, latency-sensitive environments remains impractical. In this paper, we present HARNESS-LM (HLM), a three-phase training framework for transferring the capabilities of large-scale retrievers into compact, cost-efficient models. The approach comprises: (1) training a high-performance reference ("teacher") retriever by fine-tuning a billion-parameter-scale SLM; (2) aligning query representations via an L2 objective to distill knowledge into a sub-600M parameter student encoder; and (3) applying a final contrastive refinement stage to optimize the student for retrieval performance. We also present a comprehensive empirical study of key design choices, including alignment objectives, embedding dimensionality, model scale, architecture, and optimization strategies, to identify configurations that are most effective in production settings. On a real-world Bing Ads evaluation benchmark, HLM recovers over 98% of the reference retriever's precision across multiple settings, while delivering up to 27x lower online query-encoder latency and 20x higher throughput on NVIDIA A100 GPUs. Online A/B testing on Bing Ads further shows a +1% Revenue, +0.6% Impression, and +0.4% Click uplift over the current ensemble of retrievers running in production with the deployed 190M parameter model, clearly highlighting the practical efficacy of the HLM recipe in a real-world sponsored search setting.

Vipul Gupta, Shikhar Mohan, Lakshya Kumar +4

Microsoft AI India

Online AdvertisingSmall Language ModelsInformation RetrievalEfficient Language Model InferenceKnowledge DistillationDense Retrieval
AskPDF
May 22, 2026

Is Dimensionality a Barrier for Retrieval Models?

Why does the low dimensionality of representations, typically d≈1000d\approx 1000, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin embeddings in the following retrieval model, classically studied in communication complexity [PS86] and more recently in embedding-based retrieval [WBNL26]. Let A∈{0,1}N×nA\in \{0,1\}^{N\times n} be a matrix indicating whether each of NN queries is relevant to each of nn documents. We are interested in the largest margin m>0,m>0, denoted by mrd(d,A),\mathsf{m}^{\mathsf{rd}}(d, A), for which there exist unit norm embeddings of the queries and documents {Uj}j=1N,{Vi}i=1n\{U_j\}_{j = 1}^N, \{V_i\}_{i = 1}^n with the following property. ⟨Uj,Vi⟩≥m\langle U_j, V_i\rangle \ge m whenever Aji=1A_{ji} = 1 and ⟨Uj,Vi⟩≤−m\langle U_j, V_i\rangle \le -m otherwise. A large margin is a key proxy for representation quality: it controls both robustness to perturbations and compositional generalization across queries. Our main theorem establishes that the best possible margin without a restriction on the dimension, mrd(+∞,A),\mathsf{m}^{\mathsf{rd}}(+\infty, A), can be nearly achieved in dimension d=O(mrd(+∞,A)−2log⁡n)d = O(\mathsf{m}^{\mathsf{rd}}(+\infty, A)^{-2}\log n) which improves a theorem of [BDES02]. Together with a matching lower bound in Theorem 1.5, we conclude that when A∈{0,1}(nk)×nA\in \{0,1\}^{\binom{n}{k}\times n} is the matrix containing all possible kk-sparse rows once, dimension d=O(klog⁡(n/k))d = O(k\log (n/k)) is necessary and sufficient for the maximal possible margin mrd(+∞,A)=Θ(k−1/2)\mathsf{m}^{\mathsf{rd}}(+\infty, A) = Θ(k^{-1/2}) in this setting. This fully resolves the setup of [WBNL26]. We also give several constructions for large margins when d=o(klog⁡(n/k)).d = o(k\log (n/k)). Finally, we empirically test the InfoNCE and sigmoid losses for producing large margin embeddings and demonstrate a clear advantage of the sigmoid loss.

Kiril Bangachev, Guy Bresler, Jonathan Kogan +1

Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge, MA, 02139

Dense Retrieval
AskPDF
May 21, 2026

A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for grounding large language model (LLM) outputs in retrieved evidence, thereby reducing hallucination and improving factual accuracy. Its efficacy, however, remains largely unexamined for low-resource, non-Latin-script languages such as Khmer. In this paper, we present a RAG-based question answering system for Khmer-language telecom-domain documents. We conduct a two-phase comparative evaluation. First, we benchmark three embedding models: BGE-M3 (567M), Jina-Embeddings-v3 (570M), and Qwen3-Embedding (597M), for dense retrieval over Khmer documents. BGE-M3 consistently performs best, achieving a Hit Rate@3 of 0.285, File Hit Rate@3 of 0.700, MRR@3 of 0.221, and Precision@3 of 0.112, substantially outperforming the other retrievers. Second, using BGE-M3 as the selected retriever, we evaluate five generator backends: Qwen3 (8B), Qwen3.5 (9B), Sailor2-8B-Chat, SeaLLMs-v3-7B-Chat, and Llama-SEA-LION-v2-8B-IT, on a curated golden dataset of 200 Khmer question-answer pairs. To quantify system performance, we apply six RAGAS-inspired metrics: faithfulness, answer relevance, context relevance, factual correctness, answer similarity, and answer correctness. The results show no single model dominates across all metrics: Qwen3.5-9B achieves the highest faithfulness (0.859) and context relevance (0.726), Qwen3-8B attains the highest factual correctness (0.380), and SeaLLMs-v3-7B-Chat performs best on answer relevance (0.867), answer similarity (0.836), and answer correctness (0.599). These findings highlight that retriever choice remains a major bottleneck for Khmer RAG, while generator strengths vary depending on whether the priority is grounding, factual precision, or semantic similarity.

Sereiwathna Ros, Phannet Pov, Ratanaktepi Chhor +3

Department of Computer Science, Chungbuk National University, Cheongju, South Korea · Department of Big Data, Chungbuk National University, Cheongju, South Korea · General Department of Information and Communication Technology, Ministry of Post and Telecommunications, Phnom Penh, Cambodia +2

Retrieval-Augmented GenerationMultilingual QARAG EvaluationDense Retrieval
AskPDF
May 20, 2026

DIVE: Embedding Compression via Self-Limiting Gradient Updates

High-dimensional language-model embeddings increase storage and search costs, while supervised compressors can overfit when relevance labels are scarce. We present DIVE (Dimensionality reduction with Implicit View Ensembles), a residual compression adapter codesigned with a self-limiting hinge loss, geometry distillation, and head-wise NT-Xent over implicit coordinate views. The hinge stops updating satisfied ranking constraints, while the dense objectives stabilize the compressed representation; only the first head is retained at inference. Under query-disjoint evaluation with two LLM2Vec backbones, five BEIR benchmarks, 128d and 256d outputs, and six baselines, DIVE is the strongest adapter on all five primary benchmarks. It also outperforms PCA and an autoencoder in comparisons against unsupervised compressors.

Dongfang Zhao

Contrastive LearningEmbedding CompressionDense Retrieval
AskPDF
May 19, 2026

High-Dimensional Concentration and Retrieval Instability in Embedding Spaces: Implications for Retrieval-Augmented Generation

Embedding-based retrieval systems rely on the assumption that geometric proximity in highdimensional representation spaces reflects semantic relevance. However, high-dimensional geometry induces concentration phenomena that can reduce the discriminative power of similarity measures and can destabilize nearest-neighbor retrieval. This work studies distance concentration, cosine concentration, contrast collapse, hubness, and retrieval instability through controlled numerical experiments across multiple synthetic distributions. The results show that similarity signals progressively lose contrast as dimension increases, leading to unstable retrieval behavior and structural bias in nearest-neighbor selection. A simplified Retrieval-Augmented Generation experiment further suggests that these effects can degrade grounding reliability upstream of generation. These findings motivate geometry-aware diagnostics and robustness-oriented retrieval strategies for embedding-based AI systems. The experiments are intentionally synthetic in order to isolate intrinsic geometric effects. High-dimensional embedding space Distance and cosine concentration Score-gap collapse and hubness Retrieval instability under perturbations Weak or incomplete retrieved context Potential degradation of grounding 1.

Ernesto Lopez Fune

DE · Data Empirix, Paris, France

Neural Representation GeometryRetrieval RobustnessDense Retrieval
AskPDF
May 14, 2026

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users. Despite the growing adoption of retrieval-augmented generation (RAG) in agentic search systems, existing literature lacks a systematic comparison of how retrieval strategy choice interacts with agent architecture and tool-calling paradigm. Important practical dimensions, including how tool outputs are presented to the model and how performance changes when searches must cope with more irrelevant surrounding text, remain under-explored in agent loops. This paper reports an empirical study organized into two experiments. Experiment 1 compares grep and vector retrieval on a 116-question sample from LongMemEval, using a custom agent harness (Chronos) and provider-native CLI harnesses (Claude Code, Codex, and Gemini CLI), for both inline tool results and file-based tool results that the model reads separately. Experiment 2 compares grep-only and vector-only retrieval while progressively mixing in additional unrelated conversation history, so that each query is embedded in more distracting material alongside the passages that matter. Across Chronos and the provider CLIs, grep generally yields higher accuracy than vector retrieval in our comparisons in experiment 1; at the same time, overall scores still depend strongly on which harness and tool-calling style is used, even when the underlying conversation data are the same.

Sahil Sen, Akhil Kasturi, Elias Lumer +2

PricewaterhouseCoopers, U.S.

Agentic SearchLLM Agent EvaluationLexical RetrievalInformation RetrievalLLM Agent HarnessesDense Retrieval
AskPDF
May 12, 2026

ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis

Template based single step retrosynthesis predicts reactants by selecting and applying an explicit reaction template, making each prediction traceable to a chemical transformation rule. This is useful for synthesis planning, but template based methods are often viewed as less competitive than template free models because template prediction is commonly formulated as global classification over a long tailed rule library. We argue that this weakness is not inherent to templates, but to the learning formulation. We present ConRetroBert, a dual encoder framework that reframes template based retrosynthesis as dense product template retrieval followed by candidate set listwise ranking. Stage 1 uses contrastive pretraining to learn a shared embedding space between products and reaction templates. Stage 2 refines template ranking over mined hard negative candidate sets with a multi positive listwise objective. To enable template side adaptation without destabilizing hard negative mining, ConRetroBert uses a slow moving exponential moving average template encoder for retrieval bank construction while updating the live template encoder through the ranking loss. On the local USPTO-50k benchmark, Stage 2 candidate set ranking improves top-1 reaction accuracy from 50.5% to 61.3%, while EMA stabilized template adaptation further improves it to 62.4%. Fine tuning from a leakage controlled USPTO-Full checkpoint reaches 75.4% top-1 accuracy on USPTO-50k. We also show that retrieval based template prediction is strong in the long tail of rare templates, and that many correct reactant predictions arise from alternative explicit templates rather than only the recorded positive label. Code and data are available at https://github.com/JahidBasher/ConRetroBert.

Mohammad Jahid Ibna Basher, Ali Khodabandeh Yalabadi, Ivan Garibay +1

Department of Industrial Engineering University of Central Florida Orlando, FL 32816

Dense RetrievalRetrosynthesisChemical Reaction Prediction
AskPDF
May 12, 2026

Test-Time Compute for Frozen Embedding Models through Agentic Program Search

Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain. We argue the opposite for dense retrieval, since modern small embedding models are distilled or adapted from large language model backbones and can inherit their latent test-time-compute potential. We ask how much retrieval quality a frozen embedding model gains at inference alone, with no auxiliary model and no parameters trained at deployment. An agentic loop in which a large language model writes programs over a frozen encoder API explores 144 candidates and yields twelve Pareto-optimal programs that trade inference compute for quality across cost ratios from c=1.2c{=}1.2 to 14.714.7, every one improving nDCG@10 on all 14 discovery tasks. The programs use no trainable parameters and recover classical retrieval primitives, among them reciprocal rank fusion, the Fisher linear discriminant, Rocchio pseudo-relevance feedback, and sentence-level MaxSim. Applied unmodified to nineteen held-out tasks and three unseen encoder families, a single fixed program improves the majority of tasks, with a positive median ΔΔnDCG@10 and a 54 to 57% win-rate at c≥4c{\ge}4, and the gains are largest on encoder families never seen during discovery. A matched-budget learned projection head trained on the same tasks does not transfer this way, improving in-domain retrieval by +0.20+0.20 to +0.25+0.25 nDCG@10 yet falling below baseline on every held-out encoder. Small embedding models therefore inherit usable test-time-compute potential, and a frozen encoder converts inference compute into retrieval gains that transfer to new corpora and encoders with no per-domain labels.

Han Xiao

Jina AI by Elastic

Inference-Time OptimizationText Embedding ModelsDense Retrieval
AskPDF
May 9, 2026

The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems

How do retrieval bounds compare between human episodic memory and Retrieval-Augmented Generation (RAG) systems under semantic interference? We present a unified signal detection theory (SDT) framework that applies to both, and use it to fit behavioral and computational data in matched paradigms. Both systems show logarithmic accuracy decline with association count (fan), but humans exhibit lower interference sensitivity (α/σ=0.41α/σ= 0.41) than dense passage retrieval (α/σ=0.67α/σ= 0.67), with cognitively-inspired HippoRAG falling between the two (α/σ=0.44α/σ= 0.44). Behavioral experiments (N=112N = 112) and simulations validate the framework; parameter recovery confirms identifiability (r≥.93r \geq .93) and model comparison favors the logarithmic specification over a power-law alternative (ΔΔBIC >15> 15). We discuss encoding specificity, temporal context binding, and retrieval gating as candidate mechanisms whose causal role remains to be established. Six falsifiable predictions connect cognitive memory research with AI retrieval evaluation.

Dongxin Guo, Jikun Wu, Siu-Ming Yiu

The University of Hong Kong, Hong Kong, China · Stellaris AI Limited, Hong Kong, China · Brain Investing Limited, Hong Kong, China

Computational Cognitive ModelingEpisodic MemoryRAG EvaluationDense Retrieval
AskPDF
May 8, 2026

DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models

This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding, representing each query or passage as a single mean-pooled vector. This ignores how DLMs are trained to generate responses through masked-position prediction under bidirectional attention, a capability that can provide stronger retrieval signals. We propose DiffRetriever, which uses the DLM's native masked-position prediction directly for retrieval. For each query or passage, DiffRetriever appends one or more masked positions, using the outputs as retrieval representations in a single forward pass. With one masked position, single-representation DiffRetriever already improves over DiffEmbed on the same backbones. DiffRetriever also naturally extends to multi-representation retrieval: DLMs process multiple masked positions jointly, enabling ColBERT-style fine-grained matching with little additional encoding latency. In autoregressive LLM retrievers, the same multi-representation strategy requires sequential decoding and therefore incurs much higher latency. DiffRetriever obtains the strongest aggregate effectiveness within our matched comparison, outperforming DiffEmbed, PromptReps, and RepLLaMA. Masked-position counts selected on training data transfer well across datasets, while per-query variation suggests headroom for adaptive allocation. Code is available at https://github.com/ielab/diffretriever.

Shuai Wang, Yu Yin, Shengyao Zhuang +2

The University of Queensland, Brisbane, QLD, Australia · CSIRO

Multi-Vector RetrievalDiffusion Language ModelsDense Retrieval
AskPDF
May 7, 2026

MINER: Mining Multimodal Internal Representation for Efficient Retrieval

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but store hundreds of vectors per page, incurring large index footprints and high serving costs. By contrast, dense single-vector retrievers retain storage and latency advantages but consistently lag in quality because they compress all information into a single final-layer embedding. In this work, we first conduct a layerwise diagnostic on single-vector retrievers, revealing that retrieval-relevant signal resides in internal representations. Motivated by these findings, we propose MINER (Mining Multimodal Internal RepreseNtation for Efficient Retrieval), a lightweight plug-in module that probes and fuses internal signals across transformer layers into a single compact embedding without modifying the backbone or sacrificing single-vector efficiency. The first Retrieval-Aligned Layer Probing stage attaches a lightweight probe at each layer, surfacing which dimensions carry retrieval-relevant information. The subsequent Adaptive Sparse Multi-Layer Fusion stage applies performance-adaptive neuron-level masking to the selected layers and fuses the surviving signals into the final dense vector. Across ViDoRe V1/V2/V3, MINER outperforms existing dense single-vector retrievers on the majority of benchmarks, with up to 4.5% nDCG@5 improvement over its corresponding backbone. Compared to strong late-interaction baselines, in some settings MINER substantially narrows the nDCG@55 gap to 0.20.2 while preserving the storage and serving advantages of dense retrieval.

Weien Li, Rui Song, Zeyu Li +8

McGill University · MIT - Massachusetts Institute of Technology · University of Cambridge +3

Multimodal EmbeddingVisual Document RetrievalDense Retrieval
AskPDF
May 7, 2026

SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents

As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical systems challenge. In small libraries, users may invoke skills explicitly by name, but this assumption breaks down as skill ecosystems grow under tight context and latency budgets. Despite its practical importance, skill retrieval remains underexplored, with limited benchmarks and little understanding of retrieval behavior on realistic skill libraries. To address this gap, we introduce SkillRet, a large-scale benchmark for skill retrieval in LLM agents. SkillRet contains 16,129 public agent skills, organized with structured semantic tags and a two-level taxonomy spanning 6 major categories and 18 sub-categories. It provides 63,259 training samples and 4,392 evaluation queries with disjoint skill pools, enabling both benchmarking and retrieval-oriented training. Across a diverse set of retrievers, we find that skill retrieval remains far from solved: off-the-shelf models struggle on realistic large-scale skill libraries, and prior skill-retrieval models still leave substantial headroom. Task-specific fine-tuning on SkillRet improves NDCG@10 by 12.9 points over the strongest prior retriever and by 16.2 points over the strongest off-the-shelf retriever. Our analysis further suggests that these gains arise because fine-tuned models better focus on the small skill-relevant signals within long and noisy queries. These results establish SkillRet as a strong benchmark and foundation for future research on retrieval in large-scale agent systems. We publicly release the benchmark (https://huggingface.co/datasets/ThakiCloud/SKILLRET), code (https://github.com/ThakiCloud/SKILLRET), and model checkpoints (0.6B: https://huggingface.co/ThakiCloud/SKILLRET-Embedding-0.6B; 8B: https://huggingface.co/ThakiCloud/SKILLRET-Embedding-8B).

Ryangkyung Kang, Hongcheol Cho, Youngeun Kim

ThakiCloud

AI Agent BenchmarksLLM Agent Skill RetrievalLLM AgentsDense Retrieval
AskPDF
May 5, 2026

Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems

Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide complementary evidence across iterative search and synthesis. However, existing work remains limited on both evaluation and training: benchmarks such as BRIGHT provide narrow gold sets and evaluate retrievers in isolation, while synthetic training corpora often optimize single-passage relevance rather than evidence portfolio construction. We introduce BRIGHT-Pro, an expert-annotated benchmark that expands each query with multi-aspect gold evidence and evaluates retrievers under both static and agentic search protocols. We further construct RTriever-Synth, an aspect-decomposed synthetic corpus that generates complementary positives and positive-conditioned hard negatives, and use it to LoRA fine-tune RTriever-4B from Qwen3-Embedding-4B. Experiments across lexical, general-purpose, and reasoning-intensive retrievers show that aspect-aware and agentic evaluation expose behaviors hidden by standard metrics, while RTriever-4B substantially improves over its base model.

Yilun Zhao, Jinbiao Wei, Tingyu Song +3

Yale NLP Lab · National University of Singapore · NYU Shanghai

Agentic SearchSynthetic Data GenerationIR EvaluationDense Retrieval
AskPDF
May 5, 2026

Reproducing Complex Set-Compositional Information Retrieval

Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current retrieval paradigms genuinely satisfy such constraints or exploit `semantic shortcuts'. We conduct a reproducibility study to benchmark major retrieval families and reasoning-targeted methods on QUEST and QUEST+Variants, and introduce LIMIT+, a controlled benchmark where relevance depends on arbitrary attribute predicates and constraint satisfaction, and less on pretrained knowledge. Our findings show that (i) on QUEST, the best neural retrievers achieve an effectiveness that is more than double what can be achieved with BM25 (Recall@100 >{>}0.41 vs.\ 0.20), but reasoning-targeted methods like ReasonIR and Search-R1 do not outperform general-purpose retrievers uniformly; (ii) on LIMIT+, gains fail to transfer, where the strongest QUEST method collapses from Recall@100≈{\approx}0.42 to below 0.02, while classic lexical retrieval gains to ∼{\sim}0.96. Lastly, (iii) stratifying by compositional depth reveals a consistent degradation across all methods, where algebraic sparse and lexical methods show more stable performance while dense approaches collapse. We release code and LIMIT+ data generation scripts to support future reproducibility and controlled evaluation.

Vincent Degenhart, Dewi Timman, Arjen P. de Vries +2

Radboud University · Nijmegen, NL

Query ComplexityLexical RetrievalInformation RetrievalIR EvaluationDense Retrieval
AskPDF
May 4, 2026

GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing

As the ecosystem of Large Language Model (LLM)-based agents expands rapidly, efficient and accurate Agent Discovery becomes a critical bottleneck for large-scale multi-agent collaboration. Existing approaches typically face a dichotomy: either relying on heavy-weight LLMs for intent parsing, leading to prohibitive latency (often exceeding 30 seconds), or using monolithic vector retrieval that sacrifices semantic precision for speed. To bridge this gap, we propose GRAIL (Granular Resonance-based Agent/AI Link), a novel framework achieving sub-400ms discovery latency without compromising accuracy. GRAIL introduces three key innovations: (1) SLM-Enhanced Prediction, replacing the generalized LLM parser with a specialized, fine-tuned Small Language Model (SLM) for millisecond-level capability tag prediction; (2) Pseudo-Document Expansion, augmenting agent descriptions with synthetic queries to enhance semantic density for robust dense retrieval; and (3) MaxSim Resonance, a fine-grained matching mechanism computing maximum similarity between user queries and discrete agent usage examples, effectively mitigating semantic dilution. Validated on AgentTaxo-9K, our new large-scale dataset of 9,240 agents, GRAIL reduces end-to-end discovery latency by over \textbf{79×\times} compared to LLM-parsing baselines, while significantly outperforming traditional vector search in Recall@10. This framework offers a scalable, industrial-grade solution for the real-time ``Internet of Agents."

Jinliang Xu

China Academy of Information and Communications Technology, Beijing, China

Dense Retrieval
AskPDF
May 3, 2026

Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

A classical vector retrieval problem typically considers a single query embedding vector as input and retrieves the most similar embedding vectors from a vector database. However, complex reasoning and retrieval tasks frequently require multiple query vectors, rather than a single one. In this work, we propose a retrieval method that considers multiple query vectors simultaneously and retrieves the most relevant vectors from the database using concepts from anomalous pattern detection. Specifically, our approach leverages a set of query vectors QQ (with ∣Q∣≥1|Q|\geq 1), and identifies the subset of vector dimensions within QQ that standout (anomalous) from the rest of dimensions. Next, we scan the vector database to retrieve the set of vectors that are also anomalous across the previously identified vector dimensions and return them as our retrieved set of vectors. We validate our approach on two image datasets, a text dataset, and a tabular dataset. Overall, we observe that, across most datasets, larger query sets lead to improved retrieval performance. The improvement is most pronounced when increasing the query sets from 1 to 8, while the gains become smaller beyond that.

Allassan Tchangmena A Nken, Baimam Boukar Jean Jacques, Miriam Rateike +2

1IBM · University of Galway · 3Carnegie Mellon University Africa +1

Multi-Vector RetrievalDense Retrieval
AskPDF
May 1, 2026

Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces

Transformer-based semantic encoders are effective for retrieval, but in many deployments the recurring bottleneck is online query encoding rather than offline corpus indexing. This paper studies whether, once a strong teacher representation space and corpus index are fixed, repeated neural query encoding can be replaced by a substantially lighter and analytically explicit estimator. We formulate fixed-teacher lexical-to-semantic encoding as a conditional-mean estimation problem in which the target semantic vector is represented as a noisy mixture of semantic prototypes weighted by posterior cluster probabilities. Kernel Affine Hull Machine (KAHM) geometry is used to estimate these posterior weights from inexpensive lexical features in an explicitly identified RKHS hypothesis space, and the semantic prototypes are refined by normalized least-mean-squares updates from noisy teacher embeddings. This yields a backpropagation-free query-side encoder together with an end-to-end error decomposition into posterior-approximation, finite-sample/generalization, and teacher-noise terms. We instantiate the approach on a controlled Austrian-law retrieval benchmark with 5,000 test queries, 84 candidate laws, and 10,762 aligned retrieval units, using law-specific encoders into a frozen Mixedbread embedding space. Among evaluation-matched learned adapters, KAHM achieves the strongest teacher-space reconstruction and the best rank-sensitive retrieval performance at all evaluated cutoffs. At k=20, it obtains MRR@20 = 0.504, Hit@20 = 0.694, and Top-1 Accuracy = 0.411, while reducing online per-query time by 8.53 relative to direct transformer query encoding in the reported CPU setting. The results support KAHMs as compute-efficient encoders for supervised fixed-representation deployment regimes.

Mohit Kumar, Somayeh Kargaran, Bernhard A. Moser +1

University of Rostock, Germany · Software Competence Center Hagenberg GmbH, Austria Hagenberg, Austria

Legal IRKernel MethodsText Embedding ModelsDense Retrieval
AskPDF
May 1, 2026

Toward a Scientific Discovery Engine for Weather and Climate Data: A Visual Analytics Workbench for Embedding-Based Exploration

Earth system science is producing increasingly large, high-dimensional datasets from both physics-based and AI-driven models. While embedding-based representations make these data searchable and serve as foundational building blocks for AI-driven discovery engines, nearest neighbors in latent spaces are not automatically scientifically meaningful. They may reflect real meteorological structures, or simply artifacts of preprocessing, geography, or model bias. Researchers therefore need visual tools to inspect latent space organization, trace search results back to physical evidence, and evaluate candidate representations against one another. We present an open source visual analytics workbench designed to support this provenance-aware scientific retrieval workflow. The system links distinct embedding experiments to shared source data, metadata, spatial contexts, and model configurations. It enables interactive retrieval strategy design by allowing users to issue image-level and localized patch-level queries, apply multi-constraint filters, and inspect analogs through familiar meteorological views. This facilitates a discovery loop where scientists characterize a phenomenon in a well-understood dataset and use its latent signature to probe larger archives. While we demonstrate the workbench through a tropical cyclone retrieval scenario using a vision foundation model (DINOv3) on ERA5 data, the framework is model-agnostic and designed to integrate with other embedding architectures in the future. Finally, we evaluate its out-of-core retrieval backend, demonstrating that interactive visual search over tens of millions of embeddings is highly scalable on commodity hardware.

Nihanth W. Cherukuru, Matt Rehme, Kirsten J. Mayer +4

NSF National Center for Atmospheric Research, Boulder, Colorado USA

Scientific VisualizationData VisualizationClimate ScienceVisual AnalyticsDense Retrieval
AskPDF
Apr 29, 2026

Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval

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 qq-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 qq-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.

Arne Eichholtz, Yongkang Li, Jutte Vijverberg +2

University of Amsterdam Amsterdam, The Netherlands

Learning to RankHypernetworksInformation RetrievalNeural EncodingIR EvaluationDense Retrieval
AskPDF
Apr 27, 2026

Improving Robustness of Tabular Retrieval via Representational Stability

Transformer-based table retrieval systems flatten structured tables into token sequences, making retrieval sensitive to the choice of serialization even when table semantics remain unchanged. We show that semantically equivalent serializations, such as csv\texttt{csv}, tsv\texttt{tsv}, html\texttt{html}, markdown\texttt{markdown}, and ddl\texttt{ddl}, can produce substantially different embeddings and retrieval results across multiple benchmarks and retriever families. To address this instability, we treat serialization embedding as noisy views of a shared semantic signal and use its centroid as a canonical target representation. We show that centroid averaging suppresses format-specific variation and can recover the semantic content common to different serializations when format-induced shifts differ across tables. Empirically, centroid representations outrank individual formats in aggregate pairwise comparisons across MPNet\texttt{MPNet}, BGE-M3\texttt{BGE-M3}, ReasonIR\texttt{ReasonIR}, and SPLADE\texttt{SPLADE}. We further introduce a lightweight residual bottleneck adapter on top of a frozen encoder that maps single-serialization embeddings towards centroid targets while preserving variance and enforcing covariance regularization. The adapter improves robustness for several dense retrievers, though gains are model-dependent and weaker for sparse lexical retrieval. These results identify serialization sensitivity as a major source of retrieval variance and show the promise of post hoc geometric correction for serialization-invariant table retrieval.

Kushal Raj Bhandari, Adarsh Singh, Jianxi Gao +2

Department of Computer Science Arizona State University Tempe, Arizona, USA · ScaleAI San Francisco, CA, USA

Retrieval RobustnessInformation RetrievalTable RetrievalInvariant Representation LearningDense Retrieval
AskPDF
Apr 25, 2026

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose Rabtriever, which independently encodes queries and documents, while providing comparable cross query-document comprehension capabilities to rerankers. We start from training a LLM-based generative reranker, which puts the document prior to the query and prompts the LLM to generate the relevance score by log probabilities. We then employ it as the teacher of an on-policy distillation framework, with Rabtriever as the student to reconstruct the teacher's contextual-aware query embedding. To achieve this effect, Rabtriever is first initialized from the teacher, with parameters frozen. The Joint-Embedding Predictive Architecture (JEPA) paradigm is then adopted, which integrates a lightweight, trainable predictor between LLM layers and heads, projecting the query embedding into a new hidden space, with the document embedding as the latent vector. JEPA then minimizes the distribution difference between this projected embedding and the teacher embedding. To strengthen the sampling efficiency of on-policy distillation, we also add an auxiliary loss on the reverse KL of LLM logits, to reshape the student's logit distribution. Rabtriever optimizes the teacher's quadratic complexity on the document length to linear, verified both theoretically and empirically. Experiments show that Rabtriever outperforms different retriever baselines across diverse rationale-based tasks, including empathetic conversations and robotic manipulations, with minor accuracy degradation from the reranker. Rabtriever also generalizes well on traditional retrieval benchmarks such as MS MARCO and BEIR, with comparable performance to the best retriever baseline.

Teng Chen, Sheng Xu, Feixiang Guo +4

Geely AI Lab Ningbo, Zhejiang, China

Language Model DistillationInformation RetrievalDense Retrieval
AskPDF
Apr 24, 2026

Aligning Dense Retrievers with LLM Utility via Distillation

Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based approaches leveraging LLM re-ranking often achieve superior performance but are computationally prohibitive and prone to noise inherent in perplexity estimation. We propose Utility-Aligned Embeddings (UAE), a framework designed to merge these advantages into a practical, high-performance retrieval method. We formulate retrieval as a distribution matching problem, training a bi-encoder to imitate a utility distribution derived from perplexity reduction using a Utility-Modulated InfoNCE objective. This approach injects graded utility signals directly into the embedding space without requiring test-time LLM inference. On the QASPER benchmark, UAE improves retrieval Recall@1 by 30.59%, MAP by 30.16% and Token F1 by 17.3% over the strong semantic baseline BGE-Base. Crucially, UAE is over 180x faster than the efficient LLM re-ranking methods preserving competitive performance, demonstrating that aligning retrieval with generative utility yields reliable contexts at scale.

Rajinder Sandhu, Di Mu, Cheng Chang +4

Layer 6 AI · Toronto, ON, Canada · Dalhousie University +1

Retrieval-Augmented GenerationDense Retrieval
AskPDF
Apr 24, 2026

Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench

Patent retrieval underpins critical decisions in innovation, examination, and IP strategy, yet progress has been hampered by the absence of benchmarks that reflect the diversity of real world search scenarios. We address this gap with two contributions. First, we introduce Sophiabench, a large-scale patent retrieval benchmark comprising 10,000 queries and 75,000 corpus documents stratified across ten years, eight IPC technology sections, and twelve filing jurisdictions. Unlike prior benchmarks, Sophia-bench tests retrieval using 12 different query types-from structured patent fields to AI-generated summaries-and evaluates results against citation-based ground truth enhanced with a novel domain-relevance metric (InScope). Together, these enable systematic measurement of how well models perform across query types, technology domains, and jurisdictions. Second, we introduce QaECTER, a 344M-parameter embedding model trained on patent citation graphs and multi-view self-alignment. Despite its compact size, QaECTER establishes a new state of the art for patent retrieval. It outperforms the #1 model on the English retrieval text embedding benchmark (RTEB), a model 23x larger, as well as all existing patent specific models across every query type, IPC section, and jurisdiction on Sophia-bench, with gains of up to 7.2% average NDCG@10 over the next-best model. These results are confirmed on an independent external benchmark, where QaECTER surpasses all prior models without requiring task-specific instruction prompts. Both the benchmark and the model are designed for practical deployment in large-scale patent search systems.

Younes Djemmal, You Zuo, Kim Gerdes +1

ALMAnaCH · 1AI Lab, Questel, Paris, France · 3Inria, Paris, France +3

Legal IRText Embedding ModelsIR EvaluationDense Retrieval
AskPDF