← Back to all news
arXiv AI

Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models

arXiv:2601. 09445v2 Announce Type: replace-cross Abstract: In language models (LMs), intra-memory knowledge conflict arises when inconsistent information about the same subject is encoded within the model's parametric knowledge.

Related stories

arXiv AI
Jun 19

Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference

arXiv:2606. 20245v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance across a wide range of language-based tasks by leveraging both extensive parametric knowledge and in-context learning ability, enabling them to incorporate external information provided in the input prompt.

By Huang Peng, Jiuyang Tang, Weixin Zeng, Hao Xu, Xiang Zhao
llmsagentsbenchmarks
More like this →
arXiv Computation and Language
Sep 4

Large Language Models in Resolving Contextual Knowledge Conflicts

The paper introduces a taxonomy of six types of contextual knowledge conflicts—factual, inferential, temporal, granularity, perspective, and ambiguity—and presents the ContextConflict dataset with 5,781 samples covering reasoning and summarization tasks. Experiments on nine large language models reveal that current models struggle to resolve these conflicts, exhibit a bias toward earlier evidence, and show latent awareness of conflicts in their internal representations. The authors propose a training‑free, label‑free steering method that adjusts activations to better incorporate evidence, consistently improving reasoning accuracy and producing higher‑quality, balanced summaries on the dataset.

By Xinye Yang, Zhenyang Liu, Ruisi Li, Yuanyuan Lei
llmsnlpsafety
More like this →
Hugging Face Trending Papers
Sep 2

Large Language Models in Resolving Contextual Knowledge Conflicts

The paper examines how large language models resolve conflicts that arise within contextual knowledge, rather than between internal knowledge and external context. It introduces a taxonomy of six contextual conflict types and presents the ContextConflict dataset with 5,781 samples covering reasoning and summarization tasks. Experiments on nine LLMs reveal persistent shortcomings in conflict resolution, uncover a bias toward earlier evidence, and propose a training‑free steering method that improves accuracy and summary quality.

llmsnlpsafety
More like this →
arXiv AI
Jul 28

TokenMem: Faithful Knowledge Injection for Frozen LLMs

arXiv:2607. 22625v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge, but suffers from knowledge conflicts: when retrieved information contradicts parametric memory, the shared self-attention pathway produces unpredictable outputs.

By Chengzhang Yu, Chenyang Zheng, Zening Lu, Yingru He, Yutong Huang, Yiming Zhang, Yue Xu, Zhanpeng Jin
llmsragbenchmarks
More like this →
arXiv Machine Learning
Sep 2

How Do Language Models Choose Between Context and Memory?

The paper investigates how language models decide between contextual information and their internal memory when the two conflict. By estimating "authority directions" from agreement prompts and swapping these directions between matched prompts, the authors show that such interventions can reproduce 30–68% of the shift in source choice across Qwen, Llama, and OLMo models. Cross‑task experiments reveal that authority directions learned on one task transfer only modestly (≈9%) to another, indicating that authority computations are largely task‑specific.

By Benjamin Shih, John Winnicki, Arianna Cao
llms
More like this →