knowledge-conflicts

[NeurIPS 2025] ParamMute (a.k.a. PIP-KAG): suppressing knowledge-critical FFNs for faithful retrieval-augmented generation (RAG knowledge conflicts)

[EMNLP 2023] A Causal View of Entity Bias in (Large) Language Models

Official implementation of "CSKS: Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models" (EMNLP 2025)

The Knowledge Lifecycle of Large Language Models: a unified five-stage framework for how LLMs acquire, store, retrieve, update, and forget knowledge, with the Provenance Vector proposal and the reproducible Lifecycle Desynchronization metric.

Analyzing the correlation between Hallucinations and Knowledge Conflicts in Large Language Models

Accept or Repair: Preserving Passage-Supported Answers in Contrastive Decoding

Do stale facts override new ones in agent memory? Seven memory designs, four local models, every answer checked by code

RetrievalStress: a benchmark of how LLMs handle retrieved context that conflicts with their knowledge, distracts, or spans multiple hops

Investigating intra-memory knowledge conflicts emergence in BigBird

Official code and dataset for "Contextual Knowledge Conflicts in RAG Systems with a Recipe Dataset" (AIxIA 2026). A framework for evaluating how large language models respond to conflicting recipe ingredient variants, comparing generation with oracle context against generation without context.

RIVER is a recency-invariant, validity-sensitive evidence-revision framework for reliable multi-turn retrieval-augmented generation.