What Is Seen Cannot Be Unseen: The Disruptive Effect of Knowledge Conflict on Large Language Models

ACL ARR 2025 May Submission4378 Authors

Abstract:

Large language models frequently rely on both contextual input and parametric knowledge to perform tasks.
However, these sources can come into conflict, especially when retrieved documents contradict the model’s parametric knowledge.
We propose a diagnostic framework to systematically evaluate LLM behavior under \textit{context-memory conflict}, where the contextual information diverges from their parametric beliefs.
We construct diagnostic data that elicit these conflicts and analyze model performance across multiple task types.
Our findings reveal that (1) knowledge conflict has minimal impact on tasks that do not require knowledge utilization, (2) model performance is consistently higher when contextual and parametric knowledge are aligned, (3) models are unable to fully suppress their internal knowledge even when instructed, and (4) providing rationales that explain the conflict increases reliance on contexts.
These insights raise concerns about the validity of model-based evaluation and underscore the need to account for knowledge conflict in the deployment of LLMs.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: Knowledge Conflict, Context-memory Conflict

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 4378