Knowledge Conflicts for LLMs: A Survey
This addresses the issue of trustworthiness and performance in LLMs for researchers and practitioners, but it is incremental as it synthesizes existing knowledge rather than introducing new methods.
The survey tackles the problem of knowledge conflicts in large language models (LLMs) by categorizing them into context-memory, inter-context, and intra-memory conflicts, aiming to improve LLM robustness through analysis of causes, behaviors, and solutions.
This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and reviewing available solutions, this survey aims to shed light on strategies for improving the robustness of LLMs, thereby serving as a valuable resource for advancing research in this evolving area.