LLM Grounding

LLM: Large Language Model

Overview

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

CardsList

332 papers21 papers in the last four weeks, down 38% on the four weeks before. 0.2% of all new papers.

  1. Language-model agents' beliefs can be manipulated via truthful evidence in open channel

    Nov 16, 2026Jinwei Hu, Qisong He, Xinmiao Huang +3Belief Updating in LLMsLLM Grounding

  2. SAGE-QA: Semantic-Aware, Grounded Evaluation for Closed-Context Question Answering on SQuAD 2.0

    Nov 12, 2026Chandra N Sekharan, Vishakan Umapathy, Abhishek PhadkeLLM EvaluationAutomated Evaluation

  3. Label-Efficient Document-Grounded Factuality Detection via Cross-Paraphrastic Invariance Learning

    Nov 12, 2026Chao Chen, Shanshan Lin, Dongsheng Hong +4Automated Fact-CheckingLLM Grounding

  4. HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data

    Nov 11, 2026Lingxiao Kong, Vasileios Arampatzakis, Vasileios Sevetlidis +2Knowledge Graph Question AnsweringLLM Grounding

  5. An evidence-traceable benchmark of clinical reasoning in large language models

    Nov 10, 2026Zhiqun Zhao, Xiaodong Yang, Bruce Gu +13Clinical Reasoning in Language ModelsClinical Language Model Evaluation

  6. From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow

    Nov 9, 2026Kun Feng, Chenchen Chu, Yan Liu +6LLM GroundingLLM Hallucination Mitigation

  7. Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation

    Nov 5, 2026Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh JeiraniLLM Reasoning with GraphsLanguage Model Reasoning Evaluation

  8. Variable names provide priors: semantic grounding enables data-efficient numerical prediction by large language models

    Nov 2, 2026Xin-Rui Ma, Shi-Zhi Chen, Hai-Yan Jiang +2LLM GroundingTabular Prediction

  9. GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation

    Nov 2, 2026Ekata Mitra, Yufei Tao, Kamalamalini Nagasundaram +1Text-to-SQLLLM Grounding

  10. Category-Anchored Large Language Models for Next POI Recommendation

    Oct 29, 2026Lexi Bai, Xiaopeng Zeng, Xun Zhou +2Sequential RecommendationLarge Language Model-Based Recommendation

  11. PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy

    Oct 27, 2026Vansh Bhatia, Mehdi Rezagholizadeh, Parsa Ashrafi Fashi +3MLLM EvaluationMultimodal Model Evaluation

  12. OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning

    Oct 26, 2026Hui Yang, Jiaoyan Chen, Yongsheng GaoAgentic RAGRetrieval-Augmented Generation

  13. Scoped Semantic Invariance as a Foundation for LLM Reliability

    Oct 23, 2026Rosario Uceda-Sosa, Maria Chang, Karthikeyan Natesan Ramamurthy +1Reasoning Consistency in Language ModelsLLM Reliability

  14. LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents

    Oct 23, 2026Shen Liu, Ze Zhou, Zhenguo Xu +3LLM Agent Skill RetrievalLLM Grounding

  15. When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions

    Oct 22, 2026Clemencia Siro, Laura HollinkGrounded Text GenerationLLM Grounding

  16. Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference

    Oct 22, 2026Amirhossein Aghaei, Liangyan Li, Shiyi Yang +2LLM Reasoning with GraphsLLM Grounding

  17. AI Mindmeld: A Latent Interconnect Protocol

    Oct 21, 2026Siavash Golkar, Jake Kovalic, Shirley HoLarge Language Model-Guided Scientific DiscoveryCross-Modal Representation Learning

  18. When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction

    Oct 20, 2026Jinghui Zhang, Lang Gao, Zongfang Liu +5Language Model DecodingConstrained Decoding

  19. Training Reasoning Models to Generate Diverse Scientific Ideas

    Oct 15, 2026Manya Wadhwa, Pranav Narayanan Venkit, Hiroaki Hayashi +3Diverse Text GenerationScientific Hypothesis Generation

  20. Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts

    Oct 14, 2026Yibin Lou, Yi Hu, Jianhui Chen +3Knowledge Conflicts in Language ModelsLLM Grounding

  21. Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction

    Oct 14, 2026Lingfei Qian, Yan Wang, Xueqing Peng +6Financial Language Model EvaluationDocument Information Extraction

  22. Can LLMs Access their World Knowledge for Event Prediction?

    Oct 13, 2026Zijun Wu, Zhitian Zhang, Hossein Hajimirsadeghi +2Event Time PredictionLLM Evaluation