LLM Grounding

LLM: Large Language Model

LLM grounding studies whether a model’s answers, explanations, and actions are supported by the context it receives, structured knowledge, or observations of the world. Common approaches include retrieval-augmented generation, knowledge graphs and ontologies, tool use, evidence-linked training, and verification methods that check claims or support abstention. Work also examines grounding in images, audio, video, spatial data, and interactive environments, with evaluations measuring evidence use rather than answer accuracy alone. A central challenge is that supplying evidence does not ensure models use it: parametric knowledge, misleading context, and weak evidence selection can still lead to unsupported answers, while stronger verification can add cost and latency.

Latest papers

320 papers33 papers in the last four weeks, down 13% on the four weeks before. 0.2% of all new papers.

A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models
Apr 7, 2026Maria Mahbub, Gregory M. Dams, Josh Arnold +9Clinical Information Extraction Clinical Language Model Evaluation
Oak Ridge National Laboratory, Oak Ridge, TN, USA · Program Evaluation and Resource Center, Office of Mental Health and Office of Suicide Prevention, Department of Veterans Affairs, Menlo Park, CA, USA · Vanderbilt University Medical Center, Nashville, TN, USA +4
PassiveQA: A Three-Action Framework for Epistemically Calibrated Question Answering via Supervised Finetuning
Apr 6, 2026Madhav S BaidyaSelective QA Question Answering
Indian Institute of Technology (BHU) Varanasi
GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering
Apr 6, 2026Tianyi Zhang, Andreas MarfurtQuestion Answering Document QA
getAbstract · Lucerne University of Applied Sciences and Arts Switzerland
NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models
Apr 5, 2026Deepa Tilwani, Yash Saxena, Ankur Padia +2LLM Reliability Neuro-Symbolic AI
Department of Computer Science, AI Institute, University of South Carolina, Columbia, South Carolina, USA · Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, Maryland, USA · Department of Computer Science and Engineering, The Ohio State University, Columbus, Ohio, USA
MedicalBench: Evaluating Large Language Models Toward Improved Medical Concept Extraction
Apr 5, 2026Zhichao Yang, Gregory D. Lyng, Sanjit Singh Batra +1Clinical Information Extraction Clinical Language Model Evaluation
Optum AI
Explorable Proofs: Making Written Proofs Explorable by Grounding Them in Formal Representations
Apr 3, 2026Hita Kambhamettu, Will Crichton, Sean Welleck +2LLM Grounding Interactive Theorem Proving
University of Pennsylvania Philadelphia, PA, USA · Brown University Providence, RI, USA · Carnegie Mellon University Pittsburgh, PA, USA +1
SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
Apr 2, 2026Daeyong Kwon, Soyoung Yoon, Seung-won HwangMulti-Hop QA LLM Answer Verification
Seoul National University, South Korea
Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
Apr 1, 2026Hexuan Wang, Jingyu Zhang, Benjamin Van Durme +1LLM Evaluation LLM Grounding
Department of Computer Science, Johns Hopkins University
Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents
Apr 1, 2026Thanh Luong Tuan, Abhijit SanyalOntology-Based Reasoning Enterprise AI Agents
Golden Gate University, San Francisco · Foundation AgenticOS (FAOS) · Associate Director, Data, Digital & IT, Novartis Healthcare Pvt. Ltd., Hyderabad, India
SemLoc: Structured Grounding of Free-Form LLM Reasoning for Fault Localization
Mar 31, 2026Zhaorui Yang, Haichao Zhu, Qian Zhang +2Fault Localization LLM Grounding
UC Riverside · Independent Researcher · Cisco Research
Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure
Mar 30, 2026Camilo Chacón SartoriLLM Grounding Explainability Evaluation
Institut Català de Nanociència i Nanotecnologia (ICN2). · Artificial Intelligence Research Institute (IIIA-CSIC), Barcelona, Spain.
CRAFT: Grounded Multi-Agent Coordination Under Partial Information
Mar 26, 2026Abhijnan Nath, Hannah VanderHoeven, Nikhil KrishnaswamyMulti-Agent Coordination Multi-Agent Communication
Situated Grounding and Natural Language (SIGNAL) Lab∗ Department of Computer Science, Colorado State University Fort Collins, CO 80523 USA
OMIND: Framework for Knowledge Grounded Finetuning and Multi-Turn Dialogue Benchmark for Mental Health LLMs
Mar 26, 2026Suraj Racha, Prashant Harish Joshi, Utkarsh Maurya +6Medical LLMs LLM Fine-Tuning
Indian Institute of Technology Bombay
Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale
Mar 25, 2026Chinmay Soni, Shivam Chourasia, Gaurav Kumar +1Sports Analytics Text-to-SQL
Sporta Technologies Private Limited, Mumbai, Maharashtra, India
HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents
Mar 25, 2026Lexin Wang, Shenghua Liu, Yiwei Wang +5Multimodal Model Evaluation Table QA
Institute of Computing Technology, Chinese Academy of Sciences · University of California, Merced · University of Queensland
Grounded Chess Reasoning in Language Models via Master Distillation
Mar 20, 2026Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert +4LLM Grounding CoT Distillation
Department of Computer Science, University of Toronto · Queen’s University · Coolwei AI Lab
When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal
Mar 20, 2026Yen-Ting Piao, Jay Chiehen Liao, Wei-Tang Chien +5Audio-Language Model Evaluation LLM Evaluation
National Taiwan University, Taiwan
Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models
Mar 20, 2026Sai Koneru, Elphin Joe, Christine Kirchhoff +2LLM Grounding Adversarial Robustness of Language Models
College of Information Sciences and Technology, Pennsylvania State University, USA · Department of Computer Science, Old Dominion University, Norfolk, VA
EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models
Mar 20, 2026J. Ben Tamo, Yuxing Lu, Benoit L. Marteau +2LLM Hallucination Mitigation LLM Grounding
Georgia Institute of Technology · Pekin University
Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs
Mar 19, 2026Vedant PandyaGrounded Text Generation LLM Grounding
School of Artificial Intelligence and Data Engineering (SAIDE), Indian Institute of Technology Jodhpur
Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval
Mar 18, 2026Md. Asraful Haque, Aasar Mehdi, Maaz Mahboob +1LLM Hallucination Mitigation LLM Grounding
Computational Unit, Z.H. College of Engineering & Technology, Aligarh Muslim University, India · Interdisciplinary Center for Artificial Intelligence, Aligarh Muslim University, India · Department of Computer Engineering, Aligarh Muslim University, India
A Unified Language Model for Large Scale Search, Recommendation, and Reasoning
Mar 18, 2026Marco De Nadai, Edoardo D'Amico, Max Lefarov +18Large Language Model-Based Recommendation LLM Grounding
Spotify Denmark, Spain, Germany, France, United States, United Kingdom
Attention-guided Evidence Grounding for Spoken Question Answering
Mar 17, 2026Ke Yang, Bolin Chen, Yuejie Li +5Spoken QA Multimodal QA
Ant Group Hangzhou, China
SommBench: Assessing Sommelier Expertise of Language Models
Mar 12, 2026William Brach, Tomas Bedej, Jacob Nielsen +10Multilingual Language Model Evaluation LLM Grounding
Slovak University of Technology, Bratislava, Slovakia · sommify, Helsinki, Finland · University of Southern Denmark, Odense, Denmark
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
Mar 9, 2026Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins +10Multi-Document QA LLM Agent Evaluation
Databricks
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
Mar 9, 2026Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh +7Question Answering LLM Grounding
Qatar Computing Research Institute, HBKU, Qatar
How Much Do LLMs Hallucinate in Document Q&A Scenarios? A 172-Billion-Token Study Across Temperatures, Context Lengths, and Hardware Platforms
Mar 9, 2026JV RoigHallucination in Language Models LLM Evaluation
Kamiwaza AI
Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
Mar 4, 2026Xunzhuo Liu, Bowei He, Xue Liu +2LLM Answer Verification Retrieval-Augmented Generation
Red Hat · MBZUAI, McGill University
Evaluating Large Language Models for Gait Classification Using Text-Encoded Kinematic Waveforms
Mar 4, 2026Carlo Dindorf, Jonas Dully, Rebecca Keilhauer +2LLM Evaluation Gait Analysis
Department of Sports Science, University of Kaiserslautern-Landau (RPTU), Kaiserslautern, Germany · Fraunhofer Institute for Experimental Software Engineering IESE, Kaiserslautern, Germany · German Research Center of Artificial Intelligence, Kaiserslautern, Germany
REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry
Mar 3, 2026Yuvraj AgrawalLLM Grounding LLM Agents
Adobe Inc.

Apr 7, 2026J/K move · Enter open · S save

A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models

Maria Mahbub, Gregory M. Dams, Josh Arnold, Caitlin Rizy+8

Oak Ridge National Laboratory, Oak Ridge, TN, USA · Program Evaluation and Resource Center, Office of Mental Health and Office of Suicide Prevention, Department of Veterans Affairs, Menlo Park, CA, USA · Vanderbilt University Medical Center, Nashville, TN, USA+4

Clinical Information Extraction Clinical Language Model Evaluation LLM Reliability Automated Evaluation LLM Grounding

Open paper AskPDF arXiv

Large language models (LLMs) show promise for extracting clinically meaningful information from unstructured health records, yet their translation into real-world settings is constrained by the lack of scalable and trustworthy validation approaches. Conventional evaluation methods rely heavily on annotation-intensive reference standards or incomplete structured data, limiting feasibility at population scale. We propose a multi-stage validation framework for LLM-based clinical information extraction that enables rigorous assessment under weak supervision. The framework integrates prompt calibration, rule-based plausibility filtering, semantic grounding assessment, targeted confirmatory evaluation using an independent higher-capacity judge LLM, selective expert review, and external predictive validity analysis to quantify uncertainty and characterize error modes without exhaustive manual annotation. We applied this framework to extraction of substance use disorder (SUD) diagnoses across 11 substance categories from 919,783 clinical notes. Rule-based filtering and semantic grounding removed 14.59% of LLM-positive extractions that were unsupported, irrelevant, or structurally implausible. For high-uncertainty cases, the judge LLM's assessments showed substantial agreement with subject matter expert review (Gwet's AC1=0.80). Using judge-evaluated outputs as references, the primary LLM achieved an F1 score of 0.80 under relaxed matching criteria. LLM-extracted SUD diagnoses also predicted subsequent engagement in SUD specialty care more accurately than structured-data baselines (AUC=0.80). These findings demonstrate that scalable, trustworthy deployment of LLM-based clinical information extraction is feasible without annotation-intensive evaluation.