LLM Grounding

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

25 papers in the last four weeks, up 127% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 216

Jun 14, 2026cs.CL

The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages

Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages. It remains unclear whether a fundamental behavioral link exists between the foundational LLMs and downstream variants. We investigate this question by quantifying head-level context-truthfulness scores. Across diverse LLM and MLLM lineages, including Vicuna-, Qwen2.5-, LLaMA2-, and Mistral-based models, we find that Truth Scores are strongly preserved within model families, even after instruction tuning or multimodal adaptation. We further show that this inheritance is consistent with attention-head weight preservation, and that context-truthful heads attend to query-relevant evidence. Building on this finding, we propose TruthProbe, a soft-gating strategy that amplifies context-truthful heads while preserving other head contributions. TruthProbe improves contextual truthfulness on HaluEval and reduces multimodal hallucination on POPE and CHAIR, with base-LLM Truth Scores transferring effectively to their fine-tuned LLM and MLLM descendants. Code is available at https://github.com/miso-choi/TruthProbe.

Miso Choi, Seonga Choi, Mincheol Kwon +3

Korea University, Seoul, Republic of Korea · Kakao Mobility Corp., Seongnam, Republic of Korea

LLM Grounding LLM Interpretability Multimodal Large Language Models LLM Reliability VLM Hallucination Mitigation

Jun 13, 2026cs.CL

Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback

Large language models are increasingly deployed for written pronunciation feedback in second-language (L2) English learning, under the assumption that their diagnoses are grounded in the supplied speech evidence rather than in priors from pretraining. This assumption is tested on 1,800 L2-Arctic utterances spanning six L1 backgrounds, three audio-capable LLMs, four pronunciation dimensions, and five evidence conditions ranging from a text-only baseline to numeric acoustic features and raw audio. Each (utterance x model x condition x dimension) cell is scored on three metrics: Rating Accuracy (RA) against gold labels, Evidence Coherence (EC) assessing internal consistency without ground truth, and Grounded Correctness (GC) evaluated against gold evidence. Results show three findings across models. First, rating accuracy and grounded reasoning decouple: 39.6% of judged cells contain internally coherent reasoning that supports a wrong rating, against only 15.8% where the reasoning supports a correct rating. Second, phoneme-level feedback converges to a fixed inventory of L2-English difficulty phones that recurs across all six L1 backgrounds and all evidence conditions. Third, acoustic evidence improves the rating only when the supplied feature directly probes the target dimension: textualised F0 range raises pitch-variation grounding from (0.18-0.19) to (0.45-0.62) across all three models, while stress and phoneme correctness, which require target-to-realisation alignment, remain ungrounded. The same audio waveform without textualised F0 values does not reproduce this improvement. These findings indicate that current general-purpose LLMs are more reliable as verbalisers of externally computed pronunciation evidence than as standalone diagnostic engines.

Rong Wang, Kun Sun

University of Tuebingen, Tuebingen, Germany · Tongji University, Shanghai, China

Audio-Language Model Evaluation LLM Grounding Speech Processing Language Model Bias Evaluation

Jun 11, 2026cs.CL

sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling

The extraction of structured clinical information from unstructured EHR notes is a persistent bottleneck in healthcare informatics. While large language models (LLMs) offer high performance, their deployment in clinical settings is hindered by privacy risks, inference costs, and the tendency to hallucinate beyond textual evidence. We address these challenges for the CL4Health 2026 Case Report Form (CRF) filling task by proposing a fully local, domain-adapted pipeline using the MedGemma-27B model. Our two-stage architecture, which separates binary presence classification from value extraction, enforces strict adherence to textual evidence and ensures deterministic outputs for negated, uncertain, or unknown states. By leveraging item-specific, few-shot in-context learning without external API calls or fine-tuning, our approach achieves a macro-F1 score of 0.55 on the official English test track. This result secures second place among all locally-hosted, open-source submissions. Our work demonstrates that privacy-preserving, on-premise LLM pipelines can achieve near-competitive performance with proprietary frontier models, providing a practical, data-sovereign framework for clinical NLP.

Katharina Sommer, Tristan Till, Florian Matthes

Technical University of Munich, TUM School of Computation, Information and Technology

LLM Grounding Privacy-Preserving Language Models Clinical Information Extraction Medical LLMs

Jun 11, 2026cs.CL

SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings

Large language models (LLMs) are increasingly used to access organisational documentation, including standard operating procedures (SOPs), HR policies and institutional guidelines. However, retrieval-augmented generation (RAG) systems that rely on free-form rewriting can introduce hallucinations and unstable trade-offs between completeness and conciseness, particularly in safety- and compliance-critical settings. Objectives: To evaluate extraction as a hallucination-resistant alternative to rewriting-based RAG and compare strategies that balance precision, recall and safety across document types and model scales. Methods: We compare multiple prompting strategies, including line-number-based source selection, extraction of relevant guideline sentences with explicit safety annotations, and a multi-stage pipeline that refines draft answers using supporting evidence from source guidelines. Experiments are conducted on documents of varying length and structure, including local NHS acute care and oncology guidelines and UK-wide NICE guidelines, using both frontier-scale and locally deployable models. Performance is assessed using automatic metrics and human expert evaluation of relevance and completeness. Results: Line-number selection achieves the strongest results, outperforming direct copying and safety-focused strategies across both large and small models while maintaining high term recall (up to 95%) and close alignment with source text. Safety-oriented approaches improve precision but introduce systematic omissions, while multi-stage filtering further amplifies this trade-off. Performance varies with document structure: line-based extraction excels in protocol-like content, whereas alternative strategies perform better on more verbose documents (up to 97% term recall).

Julia Ive, Felix Jozsa, Evridiki Georgaki +6

Institute of Health Informatics, University College London, London, UK · National Hospital for Neurology and Neurosurgery, Queen Square, London, UK · Somerset NHS Foundation Trust, UK +2

Retrieval-Augmented Generation LLM Grounding LLM Hallucination Mitigation RAG Evaluation

Jun 10, 2026cs.CL

Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation

Transforming a dense, abstract proverb into an engaging and morally faithful narrative requires deep cultural understanding and robust semantic grounding. We frame this problem as a \emph{constrained semantic decompression} task and study proverb-conditioned story generation as a testbed for abstraction-to-realization in large language models (LLMs). Focusing on Persian, we introduce the Proverb Aligned Narrative Dataset (PAND), pairing proverbs with human-written stories and explicit meanings. By a hybrid evaluation framework that combines human-calibrated LLM-as-a-Judge with structural metrics, we analyze model behavior across multiple prompting regimes. Our findings reveal a persistent \emph{decompression gap}: current LLMs often achieve strong surface-level fluency while failing to faithfully instantiate the underlying moral and causal structure encoded in proverbs. We further show that explicit reasoning and iterative refinement can partially mitigate these failures, suggesting that many decompression errors arise from difficulties in translating abstract meaning into narrative form rather than a complete lack of relevant knowledge. Our proposed task naturally extends to other forms of compressed cultural knowledge.

Zahra Habibzadeh, Paria Khoshtab, Amir Mesbah +1

Tehran Institute for Advanced Studies, Khatam University, Iran

LLM Evaluation LLM Grounding Moral Reasoning in Language Models LLM Prompting Conditional Generation

Jun 8, 2026stat.ML

Robust Active Learning for Few-Shot Example Selection in Text-to-SQL

Domain-specific text-to-SQL systems ground a large language model by retrieving annotated few-shot examples, and each example needs expert-written SQL. We treat the choice of which queries to annotate as constrained experimental design on the low-dimensional manifold of query embeddings, with query-dependent annotation noise, a partition matroid constraint that spreads selections across semantic domains, and an unknown covariance structure. We propose a stratified greedy algorithm that maximizes a heteroscedastic information-gain objective. We prove that the objective is monotone and submodular under query-dependent noise, so stratified greedy selection carries a 1/2-approximation guarantee under the partition constraint. Under kernel misspecification the guarantee degrades by an additive spectral term; we compute it on both experimental pools and find it too large for the bound to be quantitatively informative. To connect the design objective to the downstream task, we give a retrieval model that bounds few-shot accuracy from below by per-domain fill distance, demonstration noise, and domain coverage, and we calibrate its locality assumption on both pools. On an enterprise supply-chain corpus and on the BIRD benchmark, the selected banks improve cross-domain retrieval and end-to-end LLM SQL over random and distance-based selection at the same annotation budget. Stratified controls and pre-specified tests show that the gain comes from the partition constraint: uniform sampling within each stratum matches the full method in the oracle-label evaluations, farthest-point selection within strata adds a little at small budgets, and the noise weighting has no measurable effect. The practical advice is to annotate one example per domain per batch from the first batch on.

Arash Pourhabib

NVIDIA

Submodular Optimization LLM Grounding Active Learning Few-Shot Prompting Text-to-SQL

Jun 8, 2026cs.RO

From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs

Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but the key bottleneck, grounding scene objects to formal ontology classes, still relies on manually curated dictionaries that are brittle and do not generalize across assets. We investigate whether large language models (LLMs) can automate this grounding step for Universal Scene Description (USD) scenes as a zero-shot, training-free alternative. On a kitchen scene (125 objects) with SOMA-HOME Ontology, LLMs achieve 90-96% exact-match accuracy with descriptive names and 49-89% with abbreviated names, substantially outperforming dictionary and embedding baselines. Under fully opaque names, context-augmented prompting recovers up to 48%. Feature ablation reveals that LLMs primarily exploit semantic cues in the scene graph (sibling names and parent paths); anonymizing these cues reduces accuracy to 0-6%, while geometry alone yields only 4-17%.

Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth +1

Technical University of Berlin, Germany · Fraunhofer FOKUS, Germany

KG Construction LLM Grounding 3D Scene Understanding

Jun 7, 2026cs.CL

TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models

Large language models answer knowledge-intensive questions using both parametric memory and retrieved evidence, but neither source is uniformly reliable. Retrieval can fill knowledge gaps, yet distracting passages may override correct closed-book answers. We study this post-generation conflict as answer-level source arbitration: given Direct and RAG answers from the same frozen model, decide which source to trust. We propose TRUSTMARGIN, a training-free, plug-and-play arbitration layer that scores the two existing candidates with the model's own likelihoods. It combines a parametric-prior margin, which tests whether memory accepts the retrieved answer, with an evidence-binding margin, which discounts passage-only salience and measures question-specific support. TRUSTMARGIN selects between Direct and RAG without fine-tuning, external judges, or additional generation. Across 2WIKIMQA and CWQA with three LLaMA scales, TRUSTMARGIN consistently improves over Direct generation and BM25-RAG, recovers part of the Direct/RAG oracle gap, and generalizes to multiple training-free RAG pipelines.

Jingyan Xu, Hong Shi, Yi Shan +4

DCST, Peking University · Beijing, China

Retrieval-Augmented Generation LLM Grounding Knowledge Conflicts in Language Models LLM Reliability RAG Evaluation

Jun 6, 2026cs.CL

TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation

Tabular data is a primary medium for storing real-world information, driving many industrial applications of machine learning. Traditional predictors achieve strong predictive performance but do not provide readable, case-specific explanations essential for decision-making. Large Language Models (LLMs) can naturally bridge this gap by generating predictions alongside explanations. However, dataset-specific patterns, such as feature distributions and interactions, make tabular data difficult for LLMs to understand and reason over, while label-only fine-tuning improves performance at the cost of catastrophic forgetting. To address this problem, we propose Tri-Level Rationale Distillation (TLRD), a framework that converts label-only tabular datasets into structured rationale supervision for LLMs. TLRD uses a high-capacity teacher to synthesize a rationale corpus grounded in three complementary levels of evidence: instance-level feature, dataset-level distributional context, and comparison-level retrieved neighbors, then distills the rationale into student LLMs, enabling zero-overhead prediction and grounded explanation from raw features only. Experiments on multiple domain datasets show that TLRD significantly closes the performance gap between LLMs and state-of-the-art tree ensembles while producing grounded and readable explanations, offering a valuable reference for high-stakes decision-making.

Tianyuan Liang, Xuwei Tan, Lei Shi +6

The Ohio State University · Stevens Institute of Technology

LLM Grounding Knowledge Distillation Tabular Prediction

Jun 6, 2026cs.CL

Cross Paraphrastic Invariance Learning for Hallucination Detection

Large language models (LLMs) frequently generate hallucinations, which are unsupported by a source document. To avoid costly LLM-as-evaluator pipelines and the heavy annotation demands of existing classifiers, we propose CPIL (Cross Paraphrastic Invariance Learning), a two-stage Siamese framework that maximizes the utility of existing labeled data. Concretely, CPIL constructs informative training pairs by: (i) generating paraphrastic views of each document-claim example as positives, and explicitly aligning their representations to enforce invariance to surface form; and (ii) mining same-document, opposite-label pairs as hard negatives to sharpen document-sensitive decision boundaries. Then CPIL conduct a two-stage model training: Stage 1 performs contrastive pretraining to learn a paraphrase-invariant, grounding-aware embedding space; and Stage 2 attaches a lightweight classifier for binary groundedness. On the LLM-AggreFact benchmark (11 tasks), CPIL surpasses strong baselines concerning F1 scores with only ~1% labeled data, showing its prediction superiority and label efficiency.

Shanshan Lin, Dongsheng Hong, Sibo Ju +3

1Fuzhou University · 2Harbin Institute of Technology (Shenzhen) · 3The Hong Kong University of Science and Technology (Guangzhou)

Contrastive Learning LLM Grounding LLM Hallucination Detection Invariant Representation Learning

Jun 4, 2026cs.CL

Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions

Final-answer accuracy, retrieval recall, and citation overlap do not reveal how much answer advantage a long-context or retrieval-augmented language model actually recovers from supplied evidence. A model may answer from parametric priors, fail to use evidence that is present, or cite relevant text without converting it into the final answer. This paper introduces a four-condition diagnostic protocol for evidence-utilization evaluation under matched examples, models, prompts, and scoring rules. The protocol compares no-evidence, full-context, retrieved-evidence, and oracle-evidence reference conditions, and uses Oracle-Reference Normalized Context Utilization (ONCU) as a denominator-valid estimate of recovered oracle-reference evidence advantage. The empirical study evaluates five local open-weight models from the Qwen, Gemma, Llama, and Mistral families over Controlled-ONCU-safe16K, HotpotQA-ONCU, and 2WikiMultiHopQA-ONCU, comprising 18,000 ONCU-compatible predictions. Results show a task-dependent diagnostic pattern: controlled synthetic settings expose reduced recovery when the same evidence is embedded in long input rather than supplied compactly, while realistic multi-hop reconstructions show that full-context inputs outperform the tested retrieved inputs in denominator-free answer and evidence metrics, with ONCU supporting the same direction on oracle-improving groups. Sensitivity audits with stronger retrieval settings narrow some gaps but do not overturn the scoped interpretation. The main contribution is therefore not a single utilization ratio, but a matched diagnostic protocol that separates no-evidence answerability, oracle-evidence recoverability, full-context recovery, retrieval-conditioned recovery, denominator validity, and companion answer/evidence diagnostics.

Haizhou Xia

University of Western Ontario, Canada

LLM Evaluation LLM Grounding Long-Context Modeling RAG Evaluation

Jun 3, 2026cs.CL

SANE Schema-aware Natural-language Evaluation of Biological Data

High-throughput microscopy generates large, structured datasets capturing cellular responses to pharmacological perturbations, but accessing these datasets typically requires SQL expertise. Large language models offer a natural-language alternative, yet their tendency to hallucinate raises concerns about result reliability . We present SANE Schema-Aware Natural-language Evaluation, a novel paradigm for domain-specific text-to-SQL evaluation: schema-grounded, automatically generated benchmarks tied to real and specific experimental structure. SANE makes evaluation more scalable, systematic, and reproducible. Using SANE, we evaluate a few-shot large language model and show that, under constrained schemas with structured prompting and guardrails, accurate query generation is achievable without any model training or fine-tuning. Most failures stem from ambiguous or underspecified inputs and manifest as overly cautious clarification requests or answers to queries that should first be disambiguated, rather than incorrect SQL generation. These results indicate that few-shot large language models can provide reliable database access in well-defined domains when combined with schema-aware prompting.

Rolf Gattung, Martin Krueger, Markus Reischl

Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany.

LLM Evaluation LLM Grounding LLM Prompting Text-to-SQL Synthetic Benchmark Generation

Jun 3, 2026cs.CL

Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation

Large language models have shown strong performance in natural language generation and downstream reasoning tasks, but they still struggle with logical consistency, factual grounding, and interpretability in complex multi-step reasoning. To address these limitations, this paper proposes SGR, a stepwise reasoning enhancement framework that integrates large language models with external knowledge graphs through query-relevant subgraph generation. Given an input question, SGR first extracts key entities, relations, and constraints to construct a structured schema, then retrieves compact subgraphs from a knowledge graph using schema-guided querying. The generated subgraphs provide explicit relational evidence that guides the language model through step-by-step reasoning. In addition, SGR combines direct Cypher-based reasoning with collaborative reasoning integration, allowing candidate answers from multiple reasoning paths to be validated and aggregated according to both model confidence and graph consistency. Experiments on benchmark datasets including CWQ, WebQSP, GrailQA, and KQA Pro demonstrate that SGR improves reasoning accuracy and Hits@1 performance over standard prompting and several knowledge-enhanced baselines. Ablation studies further show that schema guidance and Neo4j-based retrieval are both crucial to the effectiveness of the framework. These results indicate that dynamically generated external subgraphs can improve the accuracy, robustness, and interpretability of LLM-based reasoning.

Xin Zhang, Yang Cao, Baoxing Wu +2

School of Information Science and Engineering, Chongqing Jiaotong University · School of Computer Science and Technology, Chongqing University of Posts and Telecommunications

LLM Grounding LLM Reasoning with Graphs Graph Retrieval-Augmented Generation Knowledge Graph Question Answering Multi-Hop Reasoning LLM Reasoning

Jun 2, 2026cs.CL

When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG

Medical question answering is a high-stakes setting where factual errors can have serious consequences. Retrieval-augmented generation (RAG) is widely viewed as a promising solution, and prior work has reported substantial gains for large medical QA models. We revisit this assumption across a broad range of open-weight instruction-tuned models spanning 7B to 72B parameters. Across five models, ten biomedical QA datasets, four retrieval methods, and four retrieval corpora, we find that retrieval yields only small and inconsistent improvements over a no-retrieval baseline, typically within 1-2 points. In contrast, the choice of backbone model has a much larger effect than the choice of retriever or corpus, and expert and layman retrieval sources perform similarly in most settings. These results suggest that the main bottleneck is not retrieval quality alone, but the model's limited ability to use retrieved evidence effectively.

Erfan Nourbakhsh, Rocky Slavin, Ke Yang +1

The University of Texas at San Antonio

Retrieval-Augmented Generation LLM Grounding Biomedical QA Biomedical IR RAG Evaluation Medical LLMs

Jun 2, 2026cs.AI

Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs

Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frameworks typically rely on predefined operators to retrieve factual knowledge from KGs and inject it into prompts for answer generation. This paradigm faces two critical bottlenecks: 1) Inflexibility: The predefined operators are limited in scope and thus lack sufficient compositional expressiveness to fully capture the complex semantics required by KG questions. 2) Unscalability: Direct injection of factual knowledge into prompts limits scalability in handling large-scale factual knowledge. To address these two bottlenecks, we propose Code-on-Graph (CoG), a programmatic reasoning framework for LLM-KG integration. Specifically, given the factual knowledge retrieved at each reasoning step, CoG first identifies the corresponding KG schemas and represents these schemas as Python classes, which serve as abstract interfaces to the retrieved facts. It then generates executable code grounded in these classes, with the retrieved facts instantiated as objects of the corresponding classes during execution. This design enables flexible code-based reasoning while avoiding the direct injection of large-scale factual knowledge into prompts. Experiments on WebQSP, CWQ, and GrailQA demonstrate that CoG outperforms prior state-of-the-art models by up to 10.5%.

Weiwei Ding, Zixuan Li, Long Bai +7

1Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · 2Shandong University · 3Shandong University-Weihai Research Institute of Industrial Technology

LLM Grounding LLM Reasoning with Graphs LLM-Based Program Synthesis Knowledge Graph Question Answering Knowledge Graphs

Jun 2, 2026cs.CL

EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge

Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spider, BIRD, and Spider~2.0 evaluate schema generalization, large-scale databases, and realistic workflows, but largely overlook enterprise scenarios where SQL generation depends on private business knowledge, such as internal metrics, reporting conventions, and organizational rules. We introduce EntSQL, an enterprise-oriented Text-to-SQL benchmark for evaluating long-context grounding over proprietary business documents. EntSQL contains 1,066 aligned Chinese-English semantic examples across five business domains, with most examples requiring domain knowledge beyond the question and schema and involving complex SQL structures. On English inputs, the best evaluated system reaches only 15.9% when long-form documents are provided, highlighting the difficulty of grounding SQL generation in enterprise knowledge.

Chengxi Liao, Tao Xu, Zulong Chen +7

1HKUST (GZ) · 2Alibaba Group · 4Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) +1

LLM Grounding Text-to-SQL

Jun 2, 2026cs.CL

Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding

Causal language models factorize sequence probabilities using only preceding context, leaving future information unexploited during training despite its availability in the training data. This paper introduces Regret Pre-training, a self-supervised framework grounded in the Learning Using Privileged Information (LUPI) paradigm. The framework employs a dual-view architecture in which a single model generates both a causal Student distribution and a future-conditioned Teacher distribution. The training objective augments standard language modeling with a regret loss that minimizes the KL divergence from teacher to student, transferring future-aware signals to the causal representations. We investigate two teacher configurations on the OLMoE-1B-7B architecture:LocalRegret, which extends attention by one future token, andGlobalRegret, which conditions on bidirectional context with the target position masked. Experiments on nine downstream tasks following 4 billion tokens of training demonstrate that both configurations consistently outperform the baseline. On average,GlobalRegret andLocalRegret achieve 33.9% and 32.2% accuracy respectively, surpassing the baseline's 30.2%. Most notably,GlobalRegret improves BoolQ performance by 18.1 percentage points (61.0% vs 42.9%). The framework introduces no additional parameters and requires only one extra inference-mode forward pass per training step.

Mingkuan Zhao, Xiayu Sun, Wentao Hu +5

The School of Computer Science and Technology, Xi’an Jiaotong University, China.

Language Model Pretraining LLM Grounding Language Model Distillation Learning Using Privileged Information

Jun 2, 2026cs.CL

Pretraining Language Models on Historical Text

We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data quality and availability, preventing temporal leakage, designing temporally consistent post-training pipelines, and constructing reliable evaluations. To address these issues, we construct TypewriterCorpus, a 54B-token historical corpus collected from diverse archival and linguistically annotated sources with extensive data cleaning and leakage mitigation procedures. Furthermore, we introduce lexically grounded instructing tuning, a post-training framework that constraints responses to remain directly grounded in historical source documents. Using this framework we construct two historical instruction tuning datasets: History-LIMA and History-SelfInstruct. To evaluate capability and temporal consistency, we introduce History-Event, a benchmark suite for evaluating competence, temporal grounding and data leakage. We release TypewriterLM and all associated resources to support future research on historical language models.

Xiaoxi Luo, Zachary Shinnick, Niclas Griesshaber +5

University of Waterloo · Vector Institute · AIML, Adelaide University +3

Language Model Pretraining LLM Evaluation LLM Grounding Language Modeling

Jun 1, 2026cs.AI

ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning

Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic health records (EHRs). In contrast, EHR foundation models can learn predictive patient representations, yet lack interpretable language-based reasoning. To bridge this gap, we propose ChatHealthAI, a multimodal reasoning framework that aligns structured EHR representations from a pretrained EHR foundation model with the semantic space of a frozen LLM through a task-aware resampler. By integrating longitudinal patient representations with refined clinical event descriptions, ChatHealthAI enables clinically grounded natural-language reasoning while maintaining accurate patient prediction. We evaluated ChatHealthAI on three clinical predictive tasks from the EHRSHOT benchmark. Results show that ChatHealthAI improves reasoning quality and interpretability while preserving competitive predictive performance. These findings highlight the potential of integrating EHR foundation models with pretrained LLMs for interpretable clinical prediction.

Bo-Hong Wang, Baicheng Peng, Ruilin Wang +3

School of Computer Science, McGill University, Montreal, QC, Canada · Mila - Quebec AI Institute, Montreal, QC, Canada

LLM Grounding LLM Alignment Clinical Outcome Prediction Clinical Reasoning Longitudinal EHR Modeling

May 30, 2026cs.CL

OCC-RAG: Optimal Cognitive Core for Faithful Question Answering

Recent progress in the development of language models has been defined by scale, with each generation absorbing more of the world's knowledge into its weights. However, many practical applications benefit more from robust reasoning than from extensive parametric knowledge. In this setting, task-specialized small language models (SLMs) offer a principled design choice. We introduce Optimal Cognitive Core (OCC), a family of SLMs built around this premise. As a variant of OCC, we present OCC-RAG, optimized for faithful question answering (QA) grounded in the provided context. This task directly aligns with the OCC design approach, requiring multi-hop reasoning over supplied passages while ignoring memorized knowledge. To train OCC-RAG, we implement a novel pipeline for synthesizing multi-context, multi-hop QA data at scale, producing a corpus of over three million examples targeting multi-hop reasoning, strict context faithfulness, and calibrated abstention. We release OCC-RAG-0.6B and OCC-RAG-1.7B, both mid-trained on this corpus. The models produce structured reasoning traces with source citations grounded in literal quotes from the context. Through OCC-RAG, we demonstrate that compact, task-specialized SLMs can match or exceed general-purpose models 2 -- 6x their size across multi-hop reasoning (HotpotQA, MuSiQue, TAT-QA), faithfulness (ConFiQA), and refusal (MuSiQue-Un) benchmarks.

Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze +7

OCC Team

Multi-Hop QA LLM Grounding Small Language Models LLM Abstention

May 29, 2026cs.CL

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive distracting content. Reinforcement learning with verifiable rewards (RLVR) has shown promise for this task, yet existing methods are limited by low-confusability distractors and sparse, outcome-only reward signals that cannot supervise intermediate reasoning steps. To address these issues, we introduce \textsc{LongTraceRL}. For data construction, we generate multi-hop questions via knowledge graph random walks and leverage search agent trajectories to build \emph{tiered distractors}: documents the agent read but did not cite (high confusability) and documents that appeared in search results but were never opened (low confusability), producing training contexts that are far more challenging than those built by random sampling or one-shot search. For reward design, we propose a \emph{rubric reward} that uses the gold entities along each reasoning chain as fine-grained, entity-level process supervision. This rubric reward is applied only to responses with correct final answers (positive-only strategy), distinguishing the reasoning quality among correct responses and preventing reward hacking. Experiments on three reasoning LLMs (4B--30B) across five long-context benchmarks demonstrate that \textsc{LongTraceRL} consistently outperforms strong baselines and encourages comprehensive, evidence-grounded reasoning. Codes, datasets and models are available at https://github.com/THU-KEG/LongTraceRL.

Nianyi Lin, Jiajie Zhang, Lei Hou +1

Tsinghua University

LLM Grounding RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards Process Supervision Long-Context Inference

May 29, 2026cs.CL

Language Models Can Resolve Reference Compositionally, But It's Not Their Native Strength: The Case of the Personal Relation Task

Do neural models, such as Large Language Models, genuinely acquire compositional abilities for interpretation of natural language? When we talk about semantic interpretation, we can distinguish two complementary aspects: establishing what an expression refers to in the world (which we call the Extensional task) and representing its sense in a structured way (which we call the Intensional task). We evaluate LLMs and humans on both tasks in the setting of the Personal Relation Task (Paperno 2022) in which, given a universe of people and their relationships with each other, one is asked to interpret a noun phrase such as "Amber's parent's friend". Here, for the Intensional task, the answer is the formula "friend(parent(amber))", and for the Extensional task, the person. We find that humans and LLMs show opposite strengths: humans perform better on Extensional than Intensional tasks, and LLMs vice versa. Our methodology brings greater nuance to the understanding of compositional abilities in modern machine learning models. Our results support the notion that the lack of referential grounding in LLM training is a crucial missing component in mimicking human-like language understanding.

Bart Evelo, Meaghan Fowlie, Denis Paperno

LLM Evaluation LLM Grounding Language Modeling

May 28, 2026cs.CL

ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law

U.S. immigration law spans thousands of pages of official policy, federal regulations, and procedural guidance that change frequently and carry high stakes for petitioners who lack legal representation. We describe the construction of ImmigrationQA, a source-grounded question-answering dataset of 17,058 pairs across 13 immigration subdomains, and the fine-tuning of a Llama 3.2 3B Instruct model on that dataset using parameter-efficient LoRA. The corpus was assembled from 11 primary and secondary sources -- including the USCIS Policy Manual, 8 CFR, BIA precedent decisions, and community Q&A -- yielding 10,056 validated canonical documents and 18,308 text chunks. Structured QA pairs were generated from these chunks using Claude Sonnet 4.6 via five mode-specific prompts, with 22 pairs rejected for insufficient source-span overlap. The fine-tuned model was evaluated against a held-out split of 993 pairs using LLM-as-judge scoring on a 101-example stratified sample. The fine-tuned model scored a mean of 1.08/3.0 (16.8% fully correct; 101-example stratified eval) versus the Llama 3 8B base model at 0.85/3.0 (4% fully correct), a relative improvement of 27% in mean score; a zero-shot Claude Sonnet baseline scored 1.52/3.0 (25% fully correct). The fine-tuned model shows concentrated improvement in procedural subdomains (travel documents, adjustment of status, nonimmigrant visas) while remaining weak on complex legal reasoning and time-sensitive statistics. The full pipeline ran for approximately $29 in cloud compute. All artifacts -- dataset, model, code, and prompt templates -- are publicly released. The system is not a substitute for legal counsel and does not reflect regulatory changes after the corpus crawl date.

Nazarii Shportun

Independent Researcher

LLM Grounding Legal QA

May 28, 2026cs.CL

When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models

Large language models (LLMs) are widely used as cross-lingual knowledge interfaces. However, culturally grounded questions often reflect globally dominant narratives rather than local contexts. We study this failure mode as \textit{global narrative dominance} in Bangla, a low-resource cultural context. We introduce \texttt{CulturalNB}, a dataset of 717 manually curated Bengali cultural instances with parallel Bangla--English question--answer pairs and supporting evidence, metadata, and sociocultural annotations. Using question-only and evidence-based prompting, we evaluate nine state-of-the-art LLMs with human and two independent LLM judges across metrics for cross-lingual consistency, language anchoring, global substitution, institutional bias, and epistemic perspective coverage. Results show that questions asked in English systematically increase global substitution and institutional framing while reducing local perspective coverage. Local evidence improves factual consistency and perspective coverage, but does not eliminate language-induced epistemic shifts. These findings suggest that cultural failures in LLMs are not only missing-knowledge errors but also failures of grounding and narrative prioritization.

Md Arid Hasan, Ruwad Naswan, Farhan Samir +2

University of Toronto · BUET · University of Illinois Urbana-Champaign

Multilingual Language Model Evaluation LLM Grounding Cross-Lingual Reasoning in Language Models Cross-Cultural Language Model Evaluation Question Answering Cultural Bias in Language Models+3

May 28, 2026cs.CL

Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models

Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the same complete user evidence, the model should still arrive at the same answer. We argue that a key reason for this gap is self-anchored drift: responses produced under partial information introduce unsupported assumptions, and those assumptions later distort the final answer. To reduce this effect, we propose Canonical-Context On-Policy Distillation (CCOPD). During training, the same base model is used in two roles: a frozen teacher conditioned on the clean FULL prompt and a trainable student that receives the same evidence incrementally through a multi-turn conversation; CCOPD aligns the student's behavior on its own trajectories with the teacher's canonical full-context behavior. Trained only on math problem conversations, CCOPD yields a 32% average relative improvement in RAW-SHARDED performance over the original base model across math and five zero-shot out-of-domain task families, while largely preserving full-context performance. Further analyses suggest that CCOPD strengthens grounding in user evidence and reduces sensitivity to contamination from earlier assistant turns.

Zizhuo Lin, Quanling Liu, Jinsheng Quan +6

Zhejiang University · University of Science and Technology of China

LLM Grounding Reasoning Consistency in Language Models Language Model Distillation On-Policy Distillation Language Model Robustness Teacher-Student Learning+1

May 28, 2026cs.CL

Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies

Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users assess the correctness of generated outputs. Existing metrics using entailment classifiers require dataset-specific threshold tuning, while LLM-based approaches often use direct prompting, which underutilises the reasoning capabilities of LLMs. We address this by formulating grounded claim factuality checking as a true/false reading comprehension task and prompting LLMs with explicit test-taking strategies for efficient reasoning. Our method reduces token usage by over 80% compared to unguided open-ended reasoning, and achieves competitive performance to more expensive alternatives across two factuality benchmarks, setting a new state of the art on one. To further reduce inference cost, we train small language models (SLMs) to replace LLMs in the checking pipeline. Using supervised fine-tuning (SFT) and a self-revision mechanism, the SLMs learn to improve their factuality judgements. Experimental results show that the resulting SLMs perform on par with strong baselines, combining low inference costs with generating supporting rationales to support interpretability. Code and datasets will be released upon acceptance.

Yuxuan Ye, Raul Santos-Rodriguez, Edwin Simpson

Intelligent Systems Laboratory University of Bristol United Kingdom

LLM Grounding Claim Verification Efficient Language Model Reasoning Efficient Language Model Inference LLM Reasoning

May 28, 2026cs.CL

Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment

Accurately simulating the decisions of a specific individual remains challenging for large language models (LLMs), partly because persona information is often provided as static descriptions that miss the values, experiences, and contextual cues needed for individual-level decision simulation. We propose an adaptive interview framework that gathers persona-relevant information through a structured three-stage dialogue: core questions, dynamic follow-ups, and a synthesized personality summary. Using the resulting interview transcripts, we evaluate whether LLMs can simulate participants' decisions in moral dilemma scenarios. We compare three conversational contexts -- Core-10 responses, the full interview dialogue, and a summarized persona representation. We find that adaptive interviewing functions less as a uniform accuracy booster and more as a selective grounding mechanism: follow-up-derived evidence is incorporated in around 40% of full-interview traces, and these follow-up-grounded predictions are more accurate than core-only grounded ones (45.5% vs. 39.3%). These findings highlight that richer persona context alone is insufficient: improvements arise only when models actually ground their decisions in user-specific evidence.

Ruoxi Su, Yuhan Liu, Jingyu Hu

Independent Researcher · University of Cambridge

LLM Grounding Human Behavior Simulation LLM Decision-Making

May 26, 2026cs.AI

The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?

Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generated hypotheses. We study KG-guided hypothesis generation for battery materials across Mistral-7B, Llama-3.1-70B, and Gemini 2.5 Flash. We perturb local KGs by varying density, ontology richness, topology, and control structure, and evaluate outputs with both provided-graph and fixed-reference metrics. Across models, KG utility is selective and model-dependent: graph context changes outputs, but no-KG outputs also recover substantial graph content from model priors. Compact top-k subgraphs often approximate full-KG behavior, including when claimed-outcome triples are held out. At the same time, compression is not unique to one semantic ranking rule, random and topology-based subsets can also recover much of the signal. These results support a redundancy-aware Compressive KG hypothesis: useful KG signal is often recoverable from compact, scientifically structured subgraphs rather than requiring the full local graph.

Shashwat Sourav, Viktoriia Baibakova, Sanjay Das +4

1Washington University in St. Louis · 2Oak Ridge National Laboratory · 3Lawrence Berkeley National Laboratory +1

LLM Grounding LLM Reasoning with Graphs Scientific Hypothesis Generation Large Language Model-Guided Scientific Discovery Knowledge Graphs

May 26, 2026cs.DB

Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations

LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes that GPT-4 agents achieve 65% on 139 industrial maintenance scenarios, and compares LLM orchestration paradigms (Agent-As-Tool vs. Plan-Execute) on a fixed data layer. We ask the orthogonal question: how much does the data model behind the tools matter? We treat a typed knowledge graph as a grounding substrate and route each question by how it is best answered: (i) LLM-generated Cypher for structured retrieval, which lifts the same GPT-4 model from 65% to 82-83%; (ii) native graph and optimization primitives, with no LLM, reaching 99% on graph-answerable scenarios; and (iii) generation-augmented knowledge (GAK) for answers absent from the data -- the engine's agent materializes the missing facts as provenance-tagged graph nodes, then answers. A recurring theme is inverted LLM usage: we constrain the LLM to query generation or one-shot enrichment from a typed schema and let the graph execute deterministically. On the 88 real AssetOpsBench failure-mode scenarios the benchmark itself flags non-deterministic -- ten equipment types absent from the graph -- GAK lifts answerability from zero to 100% of equipment types and answers 81.8% of scenarios, every materialized fact tagged source:LLM-derived for auditability. We also contribute 40 graph-native scenarios. For structured operational domains the data layer -- not the LLM orchestration -- is the primary lever, and a typed knowledge graph serves as a grounding substrate between raw industrial data and LLM reasoning.

Madhulatha Mandarapu, Sandeep Kunkunuru

VaidhyaMegha Private Limited, India

LLM Grounding Text-to-Cypher Knowledge Graph Question Answering

May 26, 2026cs.CL

The Need for an External Observer Formalizing the Sufficiency Gap: A Mathematical Extension of Mixture Identifiability and Contextual Grounding in Sequence Models

We construct a binary mixed-regime process with one deterministic textual regime and one random regime governed by an unobserved latent state. Even an ideal infinite-capacity sequence predictor that exactly recovers the text-only marginal law can become overconfident when the observed prefix is compatible with the wrong latent regime. The resulting entropy difference is not an ordinary optimization error; it is a sufficiency gap caused by marginalization over an unobserved state. We then formalize retrieval, tool use, and external grounding through an auxiliary binary signal with fidelity

γ\in [1/2,1]

. The resulting Bayesian update yields a contextual dominance threshold: a corrective signal reverses the posterior odds induced by the textual history exactly when its fidelity exceeds the text-only posterior weight assigned to the misleading regime. This threshold reduces, but does not generally eliminate, the sufficiency gap; complete closure requires perfect revelation of the relevant latent state or an equivalent verification mechanism. The analysis clarifies why temperature scaling cannot restore missing context, why grounding mechanisms must be both informative and learnably usable by the model, and why autonomous sequence models require structurally decoupled observers or verifiers in high-stakes domains.

Francesco Corielli

Contextual Faithfulness LLM Grounding Latent Variable Models Sequence Modeling