SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.08319 · EMNLP · 2024

Knowledge Conflicts for LLMs: A Survey

Wei Xu, Zhijiang Guo, Yue Zhang, Cunxiang Wang, Hongru Wang, Rongwu Xu, Zehan Qi

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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: contextmemory, 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.08319")
get_code_for_paper("2403.08319")
have("2403.08319")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.08319.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.08319.svg)](https://syntology.ai/paper/2403.08319)

Connect an agent — have() is free.