English

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

Computation and Language 2025-02-26 v2 Machine Learning

Abstract

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level uncertainty and hallucinations. We hypothesize that attention mechanisms inherently encode context utilization signals, supported by probing analysis. Based on these insights, we propose Dynamic Attention-Guided Context Decoding (DAGCD), a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding. Experiments on open-book QA datasets demonstrate DAGCD's effectiveness, yielding significant improvements in faithfulness and robustness while preserving computational efficiency.

Keywords

Cite

@article{arxiv.2501.01059,
  title  = {Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models},
  author = {Yanwen Huang and Yong Zhang and Ning Cheng and Zhitao Li and Shaojun Wang and Jing Xiao},
  journal= {arXiv preprint arXiv:2501.01059},
  year   = {2025}
}
R2 v1 2026-06-28T20:54:18.327Z