paper-with-me

홈 › Papers

Investigating Tool-Memory Conflicts in Tool-Augmented LLMs

2026-01-14 · Jiali Cheng, Rui Pan, Hadi Amiri arxiv

Tool-augmented large language models (LLMs) have powered many applications. However, they are likely to suffer from knowledge conflict. In this paper, we propose a new type of knowledge conflict -- Tool-Memory Conflict (TMC), where the internal parametric knowledge contradicts with the external tool knowledge for tool-augmented LLMs. We find that existing LLMs, though powerful, suffer from TMC, especially on STEM-related tasks. We also uncover that under different conditions, tool knowledge and parametric knowledge may be prioritized differently. We then evaluate existing conflict resolving techniques, including prompting-based and RAG-based methods. Results show that none of these approaches can effectively resolve tool-memory conflicts.

📄 PDF Abstract BibTeX arXiv:2601.09760

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

2023-05-22 · Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou 외

By providing external information to large language models (LLMs), tool augmentation (including retrieval augmentation) has emerged as a promising solution for addressing the limitations of LLMs' static parametric memory…

Retrieval

ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool Reasoning

2026-05-08 · Ye Liu, Botao Yu, Xinyi Ling, Daniel Adu-Ampratwum 외 arxiv

Reaction feasibility prediction, as a fundamental problem in computational chemistry, has benefited from diverse tools enabled by recent advances in artificial intelligence, particularly large language models. However, t…

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages

2024-02-16 · Junjie Ye, Sixian Li, Guanyu Li, Caishuang Huang 외

Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios. While current research primarily emphasizes leveraging tools to augment LLMs, it frequent…

Investigating the Adaptive Robustness with Knowledge Conflicts in LLM-based Multi-Agent Systems

2025-02-21 · Tianjie Ju, Bowen Wang, Hao Fei, Mong-Li Lee 외

Recent advances in Large Language Models (LLMs) have upgraded them from sophisticated text generators to autonomous agents capable of corporation and tool use in multi-agent systems (MASs). However, the robustness of the…

Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models

2024-02-22 · Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu 외

Retrieval-augmented language models (RALMs) have demonstrated significant potential in refining and expanding their internal memory by retrieving evidence from external sources. However, RALMs will inevitably encounter k…

Retrieval