Knowledge Conflicts in Language Models

Follow this topic Ask about this topic

Knowledge conflicts arise when a model’s learned knowledge disagrees with information in a prompt, retrieved documents, tools, or stored conversation memory. Researchers test how models handle counterfactual and outdated facts, contradictory sources, and differences in framing or evidence order, using question-answering benchmarks, retrieval tasks, and multi-turn evaluations. Approaches include conflict-aware retrieval and decoding, confidence-based abstention, fine-tuning, and interventions that probe or steer internal representations. A central challenge is deciding when to follow context and when to resist it: stronger evidence-following can improve faithfulness but also make models more vulnerable to misleading, stale, or malicious information.

Latest papers

142 papers16 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
May 29, 2026Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter +1Retrieval-Augmented Generation Language Model Decoding
Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology · Department of Civil, Construction & Environmental Engineering, Iowa State University
From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation
May 27, 2026Shuaike Li, Kai Zhang, Xianquan Wang +2Knowledge Editing Knowledge Conflicts in Language Models
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
May 26, 2026Pruthvinath Jeripity VenkataLLM Uncertainty Estimation Faithfulness of Language Model Explanations
Independent Researcher
The Future of Facts: Tracing the Factual Generation-Verification Gap
May 26, 2026Tim R. Davidson, Anja Surina, Caglar GulcehreKnowledge Conflicts in Language Models Factual Knowledge in Language Models
EPFL
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
May 26, 2026Zhe Yu, Wenpeng Xing, Chen Ye +4Language Model Safety Evaluation Knowledge Conflicts in Language Models
Binjiang Institute of Zhejiang University · Zhejiang University · Hangzhou Dianzi University +1
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
May 26, 2026Xiaotian Ye, Xiaohan Wang, Mengqi Zhang +1Knowledge Conflicts in Language Models Hallucination in Language Models
Beijing University of Posts and Telecommunications · Huazhong University of Science and Technology · Shandong University +1
Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override
May 25, 2026Han-yu WangKnowledge Conflicts in Language Models LLM Interpretability
The University of Hong Kong
Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models
May 22, 2026Maikel Yelandi Leyva-Vázquez, Florentin SmarandacheLLM Evaluation Knowledge Conflicts in Language Models
Universidad Bolivariana del Ecuador, Coordinación Académica de Posgrado, Durán, Ecuador · Universidad de Guayaquil, Guayaquil, Ecuador · Universidad Bernardo O’Higgins, Santiago, Chile +1
ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
May 17, 2026Chenyu Wang, Yueyuan Li, Yingmin Liu +1Retrieval-Augmented Generation Knowledge Conflicts in Language Models
School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China · College of Environment and Ecology, Taiyuan University of Technology, Taiyuan, China · Zhejiang University, Hangzhou, China
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
May 14, 2026Yihang Chen, Pin Qian, Su Wang +4Retrieval-Augmented Generation Knowledge Conflicts in Language Models
1Georgia Institute of Technology · 2Carnegie Mellon University · University of California San Diego
When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering
May 13, 2026Yikun Han, Mengfei Lan, Halil KilicogluSelective Prediction Healthcare
University of Illinois Urbana-Champaign
Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
May 12, 2026Yigeng Zhou, Wu Li, Yifan Lu +6Language Model Decoding Knowledge Conflicts in Language Models
Harbin Institute of Technology, Shenzhen, 518055, China · Beijing Academy of Artificial Intelligence, China · Nanyang Technological University, Singapore
To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands
May 12, 2026Fangyi Yu, Nabeel Seedat, Jonathan Richard Schwarz +1LLM Alignment Language Model Safety Evaluation
Thomson Reuters Foundational Research, 5 Canada Square, London · Imperial College London · University of Oxford
Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation
May 12, 2026Pruthvinath Jeripity VenkataLLM Grounding Knowledge Conflicts in Language Models
Independent Researcher
Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
May 11, 2026Qinghua Mao, Xi Lin, Jinze Gu +3Knowledge Editing Knowledge Conflicts in Language Models
School of Computer Science · Shanghai Jiao Tong University
Trust or Abstain? A Self-Aware RAG Approach
May 11, 2026Xi Zhu, Ziqi Wang, Kai Mei +5Retrieval-Augmented Generation Knowledge Conflicts in Language Models
Rutgers University · University of Illinois Urbana-Champaign
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
May 7, 2026Qiyao Liang, Risto Miikkulainen, Ila FieteMemorization in Language Models Knowledge Conflicts in Language Models
Massachusetts Institute of Technology · University of Texas Austin, Cognizant · Cognizant
Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
May 2, 2026Shijun Lei, Hongyu Wang, Yunji Liang +3Knowledge Conflicts in Language Models Social Bias in Language Models
Northwestern Polytechnical University · Central University of Finance and Economics
In-Context Examples Suppress Scientific Knowledge Recall in LLMs
Apr 30, 2026Chaemin Jang, Woojin Park, Hyeok Yun +2Knowledge Conflicts in Language Models Scientific Reasoning
Korea Advanced Institute of Science and Technology · Shanghai Jiao Tong University
Quantifying Prior Dominance in RAG Systems
Apr 29, 2026Barak OrLLM Grounding Knowledge Conflicts in Language Models
ArtificialGate Ltd. · Google & Reichman Tech School · Technion – Israel Institute of Technology +1
Large language models eroding science understanding: an empirical study of malignment
Apr 28, 2026Harry Collins, Hartmut Grote, Paul Newbury +2LLM Evaluation Knowledge Conflicts in Language Models
i · ii · iii
Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
Apr 28, 2026Li Ju, Junzhe Wang, Qi ZhangContextual Faithfulness Retrieval-Augmented Generation
College of Computer Science and Artificial Intelligence, Fudan University
Authority Inversion in LLM-Mediated Ubiquitous Systems: When Models Trust Users Over Sensors
Apr 28, 2026Long Zhang, Zi-bo Qin, Wei-neng ChenKnowledge Conflicts in Language Models LLM Auditing
School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
Apr 26, 2026Shuaizhi Cheng, Xiang Shi, Zhiwei Zhang +1Knowledge Conflicts in Language Models LLM Fine-Tuning
Harbin Institute of Technology · KigLand Machine Learning Lab · Imperial College London
How Large Language Models Balance Internal Knowledge with User and Document Assertions
Apr 24, 2026Shuowei Li, Haoxin Li, Wenda Chu +1LLM Sycophancy Knowledge Augmentation for Language Models
Santa Clara University · Nanyang Technological University · California Institute of Technology
DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation
Apr 17, 2026Chao LiConstrained Generative Modeling Knowledge Conflicts in Language Models
Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
Apr 14, 2026Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5Language Model Scaling Laws Knowledge Conflicts in Language Models
IIIT Delhi, India · Singapore Institute of Technology · NVIDIA +1
Benchmarking Deflection and Hallucination in Large Vision-Language Models
Apr 13, 2026Nicholas Moratelli, Christopher Davis, Leonardo F. R. Ribeiro +2VLM Evaluation Vision-Language Models
University of Modena and Reggio Emilia · Amazon AGI · University of Cambridge
Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
Apr 13, 2026Tianzhe Zhao, Jiaoyan Chen, Shuxiu Zhang +3Knowledge Conflicts in Language Models LLM Reasoning with Graphs
School of Computer Science and Technology, Xi’an Jiaotong University · Department of Computer Science, The University of Manchester · Hunan University +1
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Apr 9, 2026Zhengyi Zhao, Shubo Zhang, Zezhong Wang +7Hallucination in RAG Retrieval-Augmented Generation
The Chinese University of Hong Kong · Ministry of Education Key Laboratory of High Confidence Software Technologies, CUHK · University of International Relations +2

May 29, 2026J/K move · Enter open · S save

Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG

Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter, Anuj Sharma

Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology · Department of Civil, Construction & Environmental Engineering, Iowa State University

Retrieval-Augmented Generation Language Model Decoding Knowledge Conflicts in Language Models Evidence-Grounded Generation

Open paper AskPDF arXiv

As retrieval-augmented generation (RAG) systems scale, it becomes increasingly challenging to ensure faithful grounding in external evidence. Large language models may still prioritize parametric knowledge over retrieved information when conflicts arise. We propose a novel training-free decoding framework, Grounded Decoding, designed to improve factual consistency in RAG without modifying model parameters. Unlike standard approaches that rely on a single conditional distribution, our method constructs two matched-prompt distributions at every generation step: (1) a full RAG distribution conditioned on the query, retrieved documents, and generated prefix, and (2) a retrieval-only distribution conditioned solely on retrieved evidence and the same prefix. The final next-token distribution is derived as the unique solution to a KL-barycenter objective over the probability simplex, yielding a normalized geometric fusion of the two distributions.This formulation naturally recovers standard RAG when the grounding weight is zero and smoothly shifts probability mass toward retrieved evidence as grounding strength increases. We further introduce a conflict-aware adaptive weighting scheme that dynamically adjusts grounding based on distributional disagreement and retriever confidence. Experiments on ALCE, Natural Questions, and FActScore demonstrate consistent improvements in factual accuracy and citation quality over standard RAG and competitive decoding-time baselines, while maintaining fluency. Our results indicate that probability-level fusion provides a strong and efficient alternative to logit-level intervention methods for faithful RAG decoding.