LLM Grounding

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is available, LLMs can still produce hallucinated outputs, and the underlying mechanisms behind such failures remain poorly understood. We investigate these mechanisms and find that hallucinations arise from systematic internal dynamics rather than random noise. First, attention disproportionately concentrates toward shortcut-like structural cues rather than distributing across the full context. Second, feed-forward representations fail to ground the provided knowledge, causing the model to revert to parametric memory. Moreover, our results indicate that hallucination is consistently associated with failures in semantic grounding within feed-forward layers, while attention allocation exhibits greater task-dependent variability. Finally, we show that these mechanistic patterns generalize beyond single-hop graphs to multi-hop and tabular settings, enabling effective hallucination detection across structured knowledge formats.

Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans. We present a modular pipeline for educational analogy generation, decomposing the task into four stages: source finding, sub-concept generation, explanation generation, and evaluation. Grounded in Structure Mapping Theory, the pipeline enables systematic, stage-by-stage analysis of how model choice and input configuration affect analogy quality. We evaluate 12 state-of-the-art LLMs across six model families on two datasets with structured sub-concept annotations (SCAR and ParallelPARC), alongside seven embedding models for closed-setting retrieval. Our results show that sub-concepts substantially improve explanation quality and closed setting retrieval precision but provide limited benefit in open-ended source generation. We further introduce an LLM-as-a-judge evaluation methodology and validate its scoring against human annotations from seven annotators, finding that Claude Sonnet 4.6 aligns more reliably with human rankings than with fine-grained absolute scores. Taken together, our findings reveal cross-stage interactions that isolated studies cannot capture, and highlight sub-concept grounding as a key driver of analogy quality generation.

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.

Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.

Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchmarks evaluate this capability solely on numerical Big Five score prediction, leaving open whether models truly perceive personality through behavioral understanding or merely prejudge through superficial pattern matching. We address this gap with three contributions. (i) A new task: we formalize Grounded Personality Reasoning (GPR), which requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding. (ii) A new dataset: we release MM-OCEAN (1,104 videos, 5,320 MCQs), produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs. (iii) Benchmark and analysis: we design a three-tier evaluation (rating, reasoning, grounding) plus four sample-level failure-mode metrics: Prejudice Rate (PR), Confabulation Rate (CR), Integration-failure Rate (IR), and Holistic-grounding Rate (HR), and benchmark 27 MLLMs (13 closed, 14 open). The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%. These findings expose a disconnect between getting the right score and reasoning for the right reason, charting a roadmap for grounded social cognition in MLLMs.

Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These pathways routinely fall short for the long tail of real-world care not covered by guidelines. Most medical large language models (LLMs), however, are trained to encode common, guideline-focused medical knowledge in their parameters. Current evaluations test models primarily on recalling and reasoning with this memorized content, often in multiple-choice settings. Given the fundamental importance of evidence-based reasoning in medicine, it is neither feasible nor reliable to depend on memorization in practice. To address this gap, we introduce OGCaReBench, a free-form retrieval-focused benchmark aimed at evaluating LLMs at answering clinical questions that require going beyond typical guidelines. Extracted from published medical case reports and validated by medical experts, OGCaReBench contains long-form clinical questions requiring free-text answers, providing a systematic framework for assessing open-ended medical reasoning in rare, case-based scenarios. Our experiments reveal that even the best-performing baseline (GPT-5.2) correctly answers only 56% of our benchmark with specialized models only reaching 42%. Augmenting models with retrieved medical articles improves this performance to up to 82% (using GPT-5.2) highlighting the importance of evidence-grounding for real-world medical reasoning tasks. This work thus establishes a foundation for benchmarking and advancing both general-purpose and medical LLMs to produce reliable answers in challenging clinical contexts.

Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data. We study this via Text2Opt-Bench, a scalable benchmark of solver-verified optimization problems spanning 12 categories, from textbook linear programs to stochastic and multi-objective formulations with up to thousands of variables. Across 10+ models, we find that accuracy collapses as instance data grows, even when the formulation itself is simple. We call this the effective binding limit. We study it with a family of techniques, BIND, that externalize numeric data to structured files so the model binds data programmatically rather than transcribing from the prompt. When using an oracle for externalizing data, we recover between 12 and 27 accuracy points, confirming binding as a key -- but recoverable -- failure mode. In a deployable setting without oracle access, we validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories, with a 1.5B binding specialist alone matching a 7B end-to-end baseline.

Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontier language models. Frontier deep research products score high on existing benchmarks, making it difficult to distinguish their capabilities from current evaluation data alone. We introduce DeepWeb-Bench, a deep research benchmark that is substantially harder than existing benchmarks for the current frontier. Difficulty comes from three properties of the data itself: each task requires massive evidence collection, cross-source reconciliation, and long-horizon multi-step derivation. We represent these three sources of difficulty as four capability families (Retrieval, Derivation, Reasoning, and Calibration) and report results sliced by family. Every reference answer is accompanied by a source-provenance record with four disclosure levels and cross-source checks where available, making scores easier to audit against the underlying evidence. We evaluate DeepWeb-Bench on nine frontier models and report three findings: (1) retrieval is not the bottleneck, as retrieval failures account for only 12-14% of errors while derivation and calibration failures account for over 70%; (2) strong and weak models fail in qualitatively different ways, with strong models' errors dominated by incomplete derivation and weak models' by hallucinated precision; and (3) models exhibit genuine specialization across domains, with cross-model agreement of only rho = 0.61 and per-case disagreement reaching 18.8 percentage points. The public benchmark release includes the data, rubrics, and evaluation code.

Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but its reliability under resource-constrained, privacy-sensitive deployments remains unclear. In healthcare, where Electronic Health Record (EHR) data is complex and strictly regulated, reliance on cloud-based large language models (LLMs) introduces challenges in cost, latency, and compliance. In this work, we present a systematic evaluation of GraphRAG for EHR schema retrieval using locally deployed open-source LLMs. We implement the Microsoft GraphRAG pipeline on real-world EHR schema documentation and benchmark four models, including Llama 3.1 (8B), Mistral (7B), Qwen 2.5 (7B), and Phi-4-mini (3.8B), each deployed via Ollama on a single consumer GPU (8 GB VRAM). We evaluate indexing efficiency, knowledge graph construction, query latency, answer quality, and hallucination under both global and local retrieval modes. Our results reveal substantial differences: Llama 3.1 produces the richest knowledge graph (1,172 entities), Qwen 2.5 achieves the best answer quality (3.3/5), Phi-4-mini fails to complete the pipeline due to structured-output errors, and Mistral exhibits degenerate repetition behavior. We further show that GraphRAG exhibits a practical capacity threshold, where models below approximately 7B parameters fail to reliably produce valid structured outputs and cannot complete the pipeline. In addition, indexing and answer quality are decoupled across models, and local retrieval consistently outperforms global summarization in both latency and factual grounding, with reduced hallucination. These findings demonstrate that GraphRAG is feasible on consumer hardware while highlighting the importance of model selection and retrieval design for robust deployment in regulated settings.

Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvements in reasoning capabilities. Still, the way these models encode knowledge seems inherently flawed: by design, LLMs encode world-knowledge within their parameters. This way of representing knowledge is inherently opaque, difficult to debug and update, and prone to hallucinations. On the other hand, Knowledge Graphs can provide human-readable and easily editable world knowledge representations, and their application in knowledge-intensive tasks has consistently proven beneficial to downstream performance. Nonetheless, current integration techniques require extensive retraining or finetuning. To overcome this issue, we introduce KoRe, a methodology to encode 1-hop sub-graphs into compact discrete knowledge tokens and inject them into a LLM backbone. We test the proposed approach on three established benchmarks, and report competitive performances coupled with a significant reduction (up to 10x) in token usage. Our results show that compact discrete KG representations can efficiently and effectively be used to ground modern LLMs.

Large Language Models (LLMs) have demonstrated strong capabilities across diverse NLP applications, such as translation, text generation, and question answering. Nevertheless, they remain limited in complex settings that demand deep reasoning and logical inference. Since these models are trained on large-scale text corpora, their generation process may still introduce irrelevant, noisy, or factually inconsistent content. To mitigate this problem, we introduce SGR, a stepwise framework that enhances LLM reasoning through external subgraph generation. SGR builds query-specific subgraphs from external knowledge bases and uses their semantic structure to support multi-step inference. By grounding intermediate reasoning steps in structured external knowledge, the framework helps the model concentrate on relevant entities, relations, and supporting evidence. In particular, SGR first constructs a subgraph tailored to the input question. It then guides the model to reason progressively over the generated structure and combines multiple reasoning trajectories to obtain the final prediction. Experimental results across several benchmark datasets show that SGR achieves consistent improvements over competitive baselines, highlighting its value for improving both reasoning accuracy and factual reliability.

Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable execution required for these complex environments. We introduce HEAR, an enterprise agentic reasoner built on a Stratified Hypergraph Ontology. Its base Graph Layer virtualizes provenance-aware data interfaces, while the Hyperedge Layer encodes n-ary business rules and procedural protocols. Operating an evidence-driven reasoning loop, HEAR dynamically orchestrates ontology tools for structured multi-hop analysis without requiring LLM retraining. Evaluations on supply-chain tasks, including order fulfillment blockage root cause analysis (RCA), show HEAR achieves up to 94.7% accuracy. Crucially, HEAR demonstrates adaptive efficiency: utilizing procedural hyperedges to minimize token costs, while leveraging topological exploration for rigorous correctness on complex queries. By matching proprietary model performance with open-weight backbones and automating manual diagnostics, HEAR establishes a scalable, auditable foundation for enterprise intelligence.

Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in retrieved evidence. However, RAG systems still produce incorrect answers in many cases. Why RAG fails despite having access to external information remains poorly understood. We present a model-internal study of retrieval-augmented generation that examines how retrieved evidence influences answer generation. Using circuit tracing, we construct attribution graphs that model the flow of information through transformer layers during decoding. These graphs represent interactions among retrieved context, intermediate model activations, and generated tokens, providing a graph, circuit-level view of how external evidence is integrated into the model's reasoning process across multiple question answering benchmarks, we observe consistent structural differences: correct predictions exhibit deeper reasoning paths, more distributed evidence flow, and a more structured pattern of local connectivity, while failed predictions show shallower, fragmented, and overly concentrated evidence flow. Building on these findings, we develop a graph-based error detection framework that uses attribution-graph topology features. Furthermore, we show that attribution graphs enable targeted interventions. By reinforcing question-constrained evidence grounding, we reshape internal routing so that answer generation remains guided by the question, leading to more effective integration of retrieved information and fewer errors.

In a long conversation, an LLM may produce a fluent continuation that rests on premises the conversation has already abandoned. Context-manipulation attacks exploit precisely this weakness. We address this problem with a runtime verifier. An LLM Interpreter maps each utterance to one or more of eight epistemic operations, and then a symbolic engine applies these operations to a dependency map that records what every claim rests on and whether it still stands. Based on the dependency map, checking whether a continuation is grounded then reduces to a walk over the map, linear in its size and requiring no LLM call. Retraction propagates through the same map with a conflict-free guarantee and flags exactly the conclusions that lose support. Our experiments with five QA models demonstrate substantial improvements in QA accuracy at a low cost per query. On ReviseQA for belief revision and MemoryAgentBench's FactConsolidation split (MemAB-FC), the verifier outperforms a retrieval baseline and raises MemAB-FC single-hop accuracy from $0.46$--$0.95$ to $0.94$--$0.98$. With the verifier, even the small 7B model overtakes unaided GPT-4o. When a GPT-4o Interpreter extracts every update from raw text rather than taking the benchmarks' structured updates, the verifier still outperforms the retrieval baseline. Moreover, on MemAB-FC, QA prompts remain compact at $97$--$174$ tokens while the full-context baseline reaches $114.5$K. Retraction queries take less than a microsecond at $2000$ turns.

The growing adoption of large language models in legal practice brings both significant promise and serious risk. Legal professionals stand to benefit from AI that can reason over contracts, draft documents, and analyze sources at scale, yet the high-stakes nature of legal work demands a level of rigor that current AI systems do not provide. The central problem is not simply that LLMs hallucinate facts and references; it is that they systematically draw inferences that go beyond what the source text actually supports, presenting assumption-laden conclusions as if they were logically grounded. This proposal presents a neuro-symbolic approach to legal AI that combines the expressive power of large language models with the rigor of formal verification, aiming to make AI-assisted legal reasoning both capable and trustworthy, thus reducing the burden of manual verification without sacrificing the accountability that legal practice demands.

We present a framework for verifying the deterministic structured computations surrounding a large language model rather than the model itself, extending a Lean 4 trust-boundary architecture to the generic interfaces of modern LLM pipelines. Certificate validity is a Lean 4 kernel type-check plus a sorry-free transitive axiom audit against the trusted set {propext, Classical.choice, Quot.sound}; other assumptions are declared and partitioned by tier (mathematical placeholders, cryptographic assumptions, ML/human oracles). The technical contribution comprises three local certificate families and two operators. The families are conflict-aware bilattice grounding (with an emission-gate soundness lemma), embedding sensitivity and paraphrase stability, and Hoare-style agent action. The operators are a Maximal Certifiable Residue, which turns abstention into the maximum-weight certifiable residue with audit-logged dropped claims, and a Compositional Stability theorem, which yields a closed-form pipeline-wide perturbation budget from per-layer gains and margins. The three families plus a Universal Assurance Card consolidator form the per-call deliverable for high-stakes deployments: patent and legal retrieval, regulated finance, clinical decision support, and agentic systems with irreversible side effects. A compiled Lean 4 reference artifact (Lean v4.30.0-rc2, Mathlib) covers all 22 certificate types, with 17 of 46 kernel-audited declarations axiom-free, the rest depending only on the trusted set and declared assumptions, and zero uses of sorryAx or Lean.ofReduceBool. The three families are empirically tested through four registered pilots: bilattice grounding on adversarially perturbed HotpotQA, embedding sensitivity in short- and long-form settings, and Hoare-style agent action on a filesystem sandbox with adversarial prompt injection.

We introduce GeoBuildBench, a benchmark designed to evaluate whether large language models and multimodal agents can ground informal natural-language plane geometry problems into executable geometric constructions. Unlike existing geometry benchmarks that focus on answer correctness or static diagram interpretation, GeoBuildBench treats geometry diagram as an interactive construction task: given a textual problem, an agent must generate a domain-specific language (DSL) program to produce a diagram satisfying explicitly specified geometric objects and verifiable constraints. The benchmark features 489 Chinese textbook-style problems, curated through automated filtering and human validation to ensure text-complete, constructible problem specifications. We evaluate several state-of-the-art multimodal models in a bounded iterative setting and show that, despite reasonable success rates, models frequently exhibit structural hallucinations, missing objects, and failures to satisfy geometric constraints, with limited ability to exploit visual and constraint-based feedback for self-correction. These results highlight geometry construction as a rigorous testbed for grounded, executable reasoning beyond textual or visual plausibility. Our benchmark and code are publicly available.

Air Traffic Control (ATC) is a safety-critical domain in which incorrect interpretation of instructions may lead to severe operational consequences. While large language models (LLMs) demonstrate strong general performance, their reliability in operational ATC environments remains unclear. Existing evaluation approaches, largely based on aggregate metrics such as F1 or macro accuracy, treat all errors uniformly and fail to account for the asymmetric consequences of high-risk semantic mistakes (e.g., incorrect runway identifiers or movement constraints). To address this gap, we propose a safety-oriented, consequence-aware evaluation framework tailored to ATC operations. Our results reveal that while current LLMs achieve reasonable aggregate accuracy, their operational reliability is severely limited. Evaluated on clean transcripts, the peak Risk Score reaches only 0.69, with most models scoring below 0.6 despite high macro-F1 performance. Further analysis shows that errors concentrate in high-impact entities despite relatively stable action-type classification, indicating structural grounding deficiencies. These findings highlight the necessity of consequence-aware evaluation protocols for the responsible deployment of AI-assisted ATC systems.

The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studies find models stubbornly retain their trained answers, ignoring provided documents nearly half the time, while others find models readily defer to the document, following context approximately 96% of the time. We argue these contradictions dissolve once one recognises that prior experiments have studied three qualitatively distinct processing situations without distinguishing them. We propose a three-regime framework: Regime 1 (single-source updating, dominant predictor: evidence coherence), Regime 2 (competitive integration, dominant predictor: parametric certainty), and Regime 3 (task-appropriate selection, dominant predictor: task knowledge requirement). We formalise a distinction between parametric strength (exposure frequency) and parametric uniqueness (encoding consistency), showing empirically that these are orthogonal dimensions (r = -0.002, p = .97) with strength as the operative predictor in stable factual domains. We validate the framework across Claude Sonnet 4.6, GPT-5.5, Gemini 2.5 Flash, Llama 4 Maverick, and DeepSeek V3 using 9,970 API calls in three experimental phases. GEE logistic regression confirms the predicted Regime 2 certainty gradient for all five models (beta = -0.38 to -0.50, all p <= .013, BH-FDR corrected). A Regime 3 ablation shows task framing alone flips context-following from near-100% (contextual knowledge condition) to 6-71% (parametric knowledge condition), with all five models significant (p < .001). The certainty gradient is robust to multinomial outcome modeling, sensitivity analyses for hedging responses, and FDR correction.

Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support. These agents demonstrate statistical fluency with domain terminology but lack grounded understanding of operational semantics -- the relational structure that connects equipment identifiers, process parameters, failure codes, and regulatory constraints within a specific production context. This paper identifies and formalizes the semantic training gap: a structural disconnect between how AI systems acquire domain vocabulary through training and how manufacturing operations define meaning through ontological relationships. We demonstrate that this gap causes operationally incorrect outputs even when model responses are linguistically precise, and that in multi-agent configurations it produces a compounding failure mode we term semantic drift. To close this gap, we present an architecture that embeds manufacturing ontology directly into the AI tool layer as a typed relational configuration, enforcing semantic constraints at runtime rather than relying on model training. The architecture is formalized as a three-operation interface contract -- resolve, contextualize, annotate -- with invariants enforced by an AIOps orchestration layer. In a controlled experiment across six industry configurations (72 tool invocations using Qwen3-32B), unconstrained tool parameters produced a 43% hallucination rate for domain identifiers; ontology-grounded parameters reduced this to 0%. We validate the approach through a digital twin analytics platform demonstrating that a single codebase with domain-specific ontology configurations eliminates tool-call hallucination and achieves cross-domain configurability without application code changes.

Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent KGQA methods mainly follow the retrieval-augmented generation paradigm to ground Large Language Models~(LLMs) with structured knowledge from KGs. However, training effective models to retrieve question-relevant evidence from KGs typically requires high-quality intermediate supervision signals, such as question-relevant paths or subgraphs, which are time- and resource-intensive to obtain. We propose PathISE, a novel framework for learning high-quality intermediate supervision from answer-level labels. PathISE introduces a lightweight transformer-based estimator that estimates the informativeness of relation paths to construct pseudo path-level supervision. This supervision is then distilled into an LLM path generator, whose generated paths are grounded in the KG to provide compact evidence for inductive answer reasoning. ExtensiveISE experiments on three KGQA benchmarks show that PathISE achieves competitive or state-of-the-art KGQA performance, and provides reusable supervision signals that can enhance existing KGQA models, without relying on costly LLM-refined supervision signals. Our source code is available at https://anonymous.4open.science/r/PathISE-2F87.

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.

Abstract concepts - justice, theory, availability - have no single perceivable referent; in the human brain, their meaning emerges from a web of experiences, affect, and social context. Do large language models (LLMs) ground abstract concepts in a similar way? We study this by replicating property-generation experiments from cognitive science on 21 frontier and open-weight LLMs. Across models and experiments, we find a consistent pattern: when compared to humans, models rely too heavily on word associations, and underproduce properties tied to emotion and internal states. This yields a large and consistent grounding gap: no model exceeds a Pearson correlation r=0.37 with human responses, compared to a human-to-human ceiling above r=0.9. To better interpret this gap, we also replicate a rating experiment on grounding categories and find that here LLMs align more closely with human judgment, and alignment improves as models get larger. We then use sparse autoencoders (SAEs) to inspect whether this information is also reflected in the models' internal features, and we do identify features connected to grounding dimensions such as "sensorimotor" and "social". These findings suggest that current LLMs can recover grounding dimensions when explicitly queried, but do not recruit them in a human-like way when words are generated freely.

LLMs are increasingly used to explain personal sensing data, translating traces of activity and mood into natural-language accounts of why an anomalous day may have occurred. However, such explanations can sound coherent and personally meaningful even when the underlying evidence is sparse or missing. We introduce epistemic overreach (EO) as a measure for cases where a generated explanation implies more than the available sensing evidence can justify. To audit how often and in what forms EO occurs, we obtained anomalous-day scenarios from three longitudinal sensing datasets of college students: StudentLife, GLOBEM, and CollegeExperience. Across activity, sleep, and affect anomalies, we generated 14,922 explanations using three LLM families -- Llama, Qwen, and GPT -- under two prompting conditions: one minimally constrained prompt and another prompt explicitly instructing models to bound claims to the data. For each scenario, we varied the amount of behavioral evidence available to the model to examine whether more evidence reduces EO. We evaluated each explanation using a structured rubric, decomposing EO into the dimensions of unsupported causal attribution, unacknowledged data gaps, overconfident language, temporal inconsistency, and diagnostic inference. We find that LLMs routinely attribute anomalous days to causes without sufficient support from the data, and that this pattern replicates across datasets, anomaly types, and model families. Further, providing richer context does not reliably reduce EO; bounded prompting helps but does not eliminate it. These findings suggest that evidential grounding should be a first-order evaluation criterion for LLM-generated personal sensing explanations, alongside fluency and plausibility. We argue that personal sensing explanations require evidential discipline: systems must distinguish what is observed, what is inferred, and what remains unknown.

Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. To characterize this scenario, we identify 6 intent types from production dialogues: five are implicit and pose fundamental challenges to standard RAG pipelines, forming a critical retrieve-first bottleneck. To address these issues, we introduce intent-driven Semantic ID (SID) generation under a Generate-then-Match paradigm. With two-stage training that consists of multi-task SID alignment and GPT-4 Chain-of-Thought distillation, an LLM maps diverse intents to hierarchical SID prefixes, which are then fuzzy-matched to the current news pool to guarantee fully grounded recommendations. Profile-Aware Dual-Signal Reasoning (PADR) further enables cold-start users to obtain valid recommendations using only profiles. On a mainstream Chinese news platform, our 7B model achieves 0% hallucination and 12.4% L1 match in the 152K open-generation SID space (4x random baseline). It matches GPT-4+Hybrid RAG on L1 while surpassing it on finer-grained metrics (L2 2x, Category +1.2pp) at ~100x lower cost. Cold-start users, where existing baselines score 0%, achieve 18.0% L1 (6x random), the highest among all user groups.

Large language models (LLMs) are rapidly being adopted across various domains. However, their adoption in banking industry faces resistance due to demands for high accuracy, regulatory compliance, and the need for verifiable and grounded responses. We present a unified, data-efficient framework for training grounded domain-specific LLMs that optimizes answer quality, citation grounding, and calibrated refusal under real-world deployment constraints. First, we describe a data generation pipeline that combines LLM-as-a-Judge filtering, citation annotation, and curriculum learning with only 143M tokens. The resulting 12B model achieves high answer quality outperforming GPT-4.1 on citation grounding, with a modest citation tradeoff versus the untuned base. Second, we propose a calibrated refusal mechanism: training on 22% unanswerable examples yield a 12% "I don't know" rate, substantially improving over the base model's unsafe 4.3% rate while avoiding GPT-4.1's over-refusal (20.2%). Third, we present an end-to-end methodology spanning from data curation to quantized serving. The system is deployed at 40+ financial institutions, achieving a 7.1 percentage point improvement in query resolution (p < 0.001). Additionally, the model delivers 3-5x faster responses at 20-50x lower cost compared to GPT-4.1.

We introduce the \textbf{Concept Field} of a text corpus: a local drift field with pointwise uncertainty, estimated in sentence-embedding space from the deltas between consecutive sentences. Given a candidate sentence transition, we score its agreement with the field by $ζ$, the mean absolute z-distance between the observed delta and the field's local Gaussian estimate. The score is black-box (no model internals), corpus-attributable (every score traces to nearby corpus sentences), and admits a probabilistically motivated interpretation under a local Gaussian approximation. We support the computation with the introduction of a \textbf{Vector Sequence Database (VSDB)} that stores embeddings together with sequence-position and next-delta metadata. We evaluate this approach on two large-scale settings: hallucination-style groundedness detection over the U.S. Code of Federal Regulations, and novelty detection over Project Gutenberg. On controlled LLM-generated rewrites, Concept Fields achieve strong selective classification performance under a grounded / ungrounded / unsure triage policy. Unlike retrieval-centric baselines, the resulting coverage-risk behavior is similar across both domains, supporting a degree of cross-domain stability for the standardized deviation score. We also sketch how divergence and curl of the Concept Field, computed on dense clusters, surface qualitatively meaningful semantic patterns (logic sources, sinks, and implicit topics), which we offer as hypothesis-generating rather than as a quantitative result. Concept Fields provide a fast, lightweight, and interpretable signal for groundedness and novelty, complementary to LLM-as-judge and white-box detectors.

The deployment of large language models (LLMs) in specialized domains like medical diagnostics and financial advisory necessitates evaluating capabilities beyond general knowledge. Traditional question-answering benchmarks often fail to capture the nuanced contextual grounding, user awareness, and domain understanding these fields require. To address this, we introduce CANDI-QA (Contextual Alignment for Niche Domains Question Answering), a novel dataset evaluating LLMs on delivering accurate, context-sensitive, and user-aligned answers in specialized settings. CANDI-QA features expert-curated question-answer pairs structured into two categories: (1) Information Assistance Questions, which are direct, factual queries requiring precise extraction, and (2) Applied Inference Questions, which are multi-hop reasoning tasks needing situational inference to generate actionable insights. We evaluate over ten diverse language models, from compact open-source to state-of-the-art proprietary systems. As a robust baseline, we present MTSS-Net, a lightweight neuro-symbolic framework combining neural retrieval with rule-based reasoning. Our findings highlight the profound challenges of achieving contextual alignment in niche domains, revealing the limitations of current LLMs without enhanced contextual or symbolic integration. Ultimately, CANDI-QA serves as a critical benchmark for advancing research in context-aware language models, stimulating the development of robust, trustworthy AI for high-stakes domains.

Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness. This blindspot leaves a logical alignment gap -- SFT models reach NLI entailment of only 0.05-0.22 despite producing fluent text. We propose RLearner-LLM with Hybrid-DPO: an automated preference pipeline that fuses a DeBERTa-v3 NLI signal with a verifier LLM score, removing human annotation while overcoming the "alignment tax" of single-signal optimization. Evaluated across five academic domains (Biology, Medicine, Law) with three base architectures (LLaMA-2-13B, Qwen3-8B, Gemma 4 E4B-it), RLearner-LLM yields up to 6x NLI improvement over SFT, with NLI gains in 11 of 15 cells and consistent answer-coverage gains. On Gemma 4 E4B-it (4.5B effective params), Hybrid-DPO lifts NLI in four of five domains (+11.9% to +2.4x) with faster inference across all five, scaling down to compact base models without losing the alignment-tax mitigation. Our Qwen3-8B RLearner-LLM wins 95% of pairwise comparisons against its own SFT baseline; GPT-4o-mini in turn wins 95% against our concise output -- alongside the 69% win the same judge gives a verbose SFT over our DPO model, this replicates verbosity bias on a frontier comparator and motivates logic-aware metrics (NLI, ACR) over LLM-as-a-judge for knowledge-intensive generation.

This paper presents the joint participation of the BIT.UA and AAUBS groups in the ArchEHR-QA 2026 shared task, which focuses on clinical question answering and evidence grounding in a low-resource setting. Due to the absence of training data and the strict data privacy constraints inherent to the healthcare domain (e.g. GDPR), we investigate the capabilities of Large Language Models (LLMs) without weight updates. We evaluate several state-of-the-art proprietary models and locally deployable open-source alternatives using various prompt engineering strategies, including task decomposition, Chain-of-Thought, and in-context learning. Furthermore, we explore majority voting and LLM-as-a-judge ensembling techniques to maximize predictive robustness. Our results demonstrate that while proprietary models exhibit strong resilience to prompt variations, domain-adapted open-source models (such as MedGemma 3 27B) achieve highly competitive performance when paired with the right prompt. Overall, our prompt-based approach proved highly effective, securing 1st place in Subtask 4 (evidence citation alignment) and 3rd place in Subtask 3 (patient-friendly answer generation). All code, results, and prompts are available on our GitHub repository: https://github.com/bioinformatics-ua/ArchEHR-QA-2026.