paper-with-me

Papers

Attention-Guided Layer Selection for Contrastive Decoding in Large Language Models

2026-07-25 · Yusuke Sakai, Natthawut Kertkeidkachorn, Kiyoaki Shirai arxiv

Contrastive decoding methods such as DoLa improve the factuality of Large Language Models (LLMs) by contrasting the output distributions of mature and premature layers. However, DoLa's dynamic layer selection relies solely on divergences in output vocabulary distributions. In this work, we propose three attention-guided strategies: Attention-JSD, Attention-Entropy-Max, and Attention-Entropy-Min, which leverage structural information carried by internal self-attention mechanisms as a signal for layer selection. Experimental results on TruthfulQA demonstrate that our strategies, particularly Attention-JSD and Attention-Entropy-Min, consistently outperform the original DoLa. We observe significant gains on multi-answer metrics (MC2 and MC3), suggesting that attention distributions can provide a more sensitive signal for resolving factual knowledge than output vocabulary distributions.

📄 PDF Abstract BibTeX arXiv:2607.23067

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation

2026-04-11 · Yebo Wu, Han Jin, Zhijiang Guo, Li Li arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual content. In this paper, we introduce Dual-An…

LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers

2025-07-06 · Jingze Zhu, Yongliang Wu, Wenbo Zhu, Jiawang Cao 외 arxiv

Large language models (LLMs) excel at natural language understanding and generation but remain vulnerable to factual errors, limiting their reliability in knowledge-intensive tasks. While decoding-time strategies provide…

Natural Language Understanding

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation

2025-05-29 · Hongxiang Zhang, Hao Chen, Tianyi Zhang, Muhao Chen

Recent decoding methods improve the factuality of large language models~(LLMs) by refining how the next token is selected during generation. These methods typically operate at the token level, leveraging internal represe…

Decision MakingHallucinationLanguage ModelingLanguage Modelling+2

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models

2024-04-14 · Souvik Das, Lifeng Jin, Linfeng Song, Haitao Mi 외

Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniqu…

Hallucination

MACD: Model-Aware Contrastive Decoding via Counterfactual Data

2026-02-02 · Qixin Xiao, Kun Zhou arxiv

Video language models (Video-LLMs) are prone to hallucinations, generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased. Existing methods, such as contrastive decoding (CD), rely on…