Knowledge Conflicts in Language Models

Overview

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 Researchers test how models handle counterfactual and outdated facts, contradictory sources, and differences in framing or evidence order, using question-answering benchmarks, retrieval tasks, and multi-turn evaluations.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

CardsList

155 papers17 papers in the last four weeks, down 11% on the four weeks before. 0.1% of all new papers.

  1. Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

    Nov 3, 2025Sekh Mainul Islam, Pepa Atanasova, Isabelle AugensteinDisentangled Representation LearningLLM Grounding

  2. When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence

    Aug 21, 2025Yufeng Zhao, Junnan Liu, Hongwei Liu +4Belief RevisionKnowledge Conflicts in Language Models

  3. Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts

    Aug 2, 2025Xianda Zheng, Zijian Huang, Meng-Fen Chiang +4Knowledge Conflicts in Language Models

  4. ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

    Feb 21, 2025Pengcheng Huang, Zhenghao Liu, Yukun Yan +8Retrieval-Augmented GenerationKnowledge Conflicts in Language Models