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

All topics

The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages
Jun 14, 2026Miso Choi, Seonga Choi, Mincheol Kwon +3LLM Grounding LLM Interpretability
Korea University, Seoul, Republic of Korea · Kakao Mobility Corp., Seongnam, Republic of Korea
Prior over Evidence: Stereotype-Driven Diagnosis in LLM-Based L2 Pronunciation Feedback
Jun 13, 2026Rong Wang, Kun SunAudio-Language Model Evaluation LLM Grounding
University of Tuebingen, Tuebingen, Germany · Tongji University, Shanghai, China
sebis at CRF Filling 2026: A Two-Stage Local LLM Pipeline for Medical CRF Filling
Jun 11, 2026Katharina Sommer, Tristan Till, Florian MatthesLLM Grounding Privacy-Preserving Language Models
Technical University of Munich, TUM School of Computation, Information and Technology
SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings
Jun 11, 2026Julia Ive, Felix Jozsa, Evridiki Georgaki +6Retrieval-Augmented Generation LLM Grounding
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
Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
Jun 10, 2026Zahra Habibzadeh, Paria Khoshtab, Amir Mesbah +1LLM Evaluation LLM Grounding
Tehran Institute for Advanced Studies, Khatam University, Iran
Robust Active Learning for Few-Shot Example Selection in Text-to-SQL
Jun 8, 2026Arash PourhabibSubmodular Optimization LLM Grounding
NVIDIA
From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs
Jun 8, 2026Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth +1KG Construction LLM Grounding
Technical University of Berlin, Germany · Fraunhofer FOKUS, Germany
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
Jun 7, 2026Jingyan Xu, Hong Shi, Yi Shan +4Retrieval-Augmented Generation LLM Grounding
DCST, Peking University · Beijing, China
TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation
Jun 6, 2026Tianyuan Liang, Xuwei Tan, Lei Shi +6LLM Grounding Knowledge Distillation
The Ohio State University · Stevens Institute of Technology
Cross Paraphrastic Invariance Learning for Hallucination Detection
Jun 6, 2026Shanshan Lin, Dongsheng Hong, Sibo Ju +3Contrastive Learning LLM Grounding
1Fuzhou University · 2Harbin Institute of Technology (Shenzhen) · 3The Hong Kong University of Science and Technology (Guangzhou)
Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions
Jun 4, 2026Haizhou XiaLLM Evaluation LLM Grounding
University of Western Ontario, Canada
SANE Schema-aware Natural-language Evaluation of Biological Data
Jun 3, 2026Rolf Gattung, Martin Krueger, Markus ReischlLLM Evaluation LLM Grounding
Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany.
Stepwise Reasoning Enhancement for LLMs via External Subgraph Generation
Jun 3, 2026Xin Zhang, Yang Cao, Baoxing Wu +2LLM Grounding LLM Reasoning with Graphs
School of Information Science and Engineering, Chongqing Jiaotong University · School of Computer Science and Technology, Chongqing University of Posts and Telecommunications
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
Jun 2, 2026Erfan Nourbakhsh, Rocky Slavin, Ke Yang +1Retrieval-Augmented Generation LLM Grounding
The University of Texas at San Antonio
Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs
Jun 2, 2026Weiwei Ding, Zixuan Li, Long Bai +7LLM Grounding LLM Reasoning with Graphs
1Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · 2Shandong University · 3Shandong University-Weihai Research Institute of Industrial Technology
EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge
Jun 2, 2026Chengxi Liao, Tao Xu, Zulong Chen +7LLM Grounding Text-to-SQL
1HKUST (GZ) · 2Alibaba Group · 4Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) +1
Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
Jun 2, 2026Mingkuan Zhao, Xiayu Sun, Wentao Hu +5Language Model Pretraining LLM Grounding
The School of Computer Science and Technology, Xi’an Jiaotong University, China.
Pretraining Language Models on Historical Text
Jun 2, 2026Xiaoxi Luo, Zachary Shinnick, Niclas Griesshaber +5Language Model Pretraining LLM Evaluation
University of Waterloo · Vector Institute · AIML, Adelaide University +3
ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning
Jun 1, 2026Bo-Hong Wang, Baicheng Peng, Ruilin Wang +3LLM Grounding LLM Alignment
School of Computer Science, McGill University, Montreal, QC, Canada · Mila - Quebec AI Institute, Montreal, QC, Canada
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
May 30, 2026Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze +7Multi-Hop QA LLM Grounding
OCC Team
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
May 29, 2026Nianyi Lin, Jiajie Zhang, Lei Hou +1LLM Grounding RL for Language Model Reasoning
Tsinghua University
Language Models Can Resolve Reference Compositionally, But It's Not Their Native Strength: The Case of the Personal Relation Task
May 29, 2026Bart Evelo, Meaghan Fowlie, Denis PapernoLLM Evaluation LLM Grounding
ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
May 28, 2026Nazarii ShportunLLM Grounding Legal QA
Independent Researcher
When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models
May 28, 2026Md Arid Hasan, Ruwad Naswan, Farhan Samir +2Multilingual Language Model Evaluation LLM Grounding
University of Toronto · BUET · University of Illinois Urbana-Champaign
Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
May 28, 2026Zizhuo Lin, Quanling Liu, Jinsheng Quan +6LLM Grounding Reasoning Consistency in Language Models
Zhejiang University · University of Science and Technology of China
Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies
May 28, 2026Yuxuan Ye, Raul Santos-Rodriguez, Edwin SimpsonLLM Grounding Claim Verification
Intelligent Systems Laboratory University of Bristol United Kingdom
Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment
May 28, 2026Ruoxi Su, Yuhan Liu, Jingyu HuLLM Grounding Human Behavior Simulation
Independent Researcher · University of Cambridge
The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
May 26, 2026Shashwat Sourav, Viktoriia Baibakova, Sanjay Das +4LLM Grounding LLM Reasoning with Graphs
1Washington University in St. Louis · 2Oak Ridge National Laboratory · 3Lawrence Berkeley National Laboratory +1
Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
May 26, 2026Madhulatha Mandarapu, Sandeep KunkunuruLLM Grounding Text-to-Cypher
VaidhyaMegha Private Limited, India
The Need for an External Observer Formalizing the Sufficiency Gap: A Mathematical Extension of Mixture Identifiability and Contextual Grounding in Sequence Models
May 26, 2026Francesco CorielliContextual Faithfulness LLM Grounding

Jun 14, 2026, cs.CLJ/K move · Enter open · S save

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

Miso Choi, Seonga Choi, Mincheol Kwon, Woosung Joung+2

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

Open paper AskPDF arXiv

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.

Momentum

Related topics

Latest papers 216