Skip to main navigation Skip to search Skip to main content

ALW: Adaptive Layer-Wise contrastive decoding enhancing reasoning ability in Large Language Models

  • Yuechi Zhou
  • , Chuyue Zhou
  • , Jianxin Zhang
  • , Juntao Li*
  • , Min Zhang
  • *Corresponding author for this work
  • Soochow University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Large language models (LLMs) have achieved remarkable performance across various reasoning tasks. However, many LLMs still encounter challenges in reasoning, especially for LLMs with fewer parameters or insufficient pre-training data. Through our experiments, we identify that noise accumulation across layers often leads to unstable token predictions during reasoning. We find that contrasting the probability distributions across layers effectively mitigates this interference. Building on this insight, we propose Adaptive Layer-Wise contrastive decoding (ALW), a novel framework that enhances reasoning ability by dynamically disentangling noise in shallow layers from critical signals in deep layers. Extensive experiments on several reasoning benchmarks demonstrate that ALW consistently improves answer accuracy across multiple LLMs while maintaining inference efficiency. For example, we achieve a 48% improvement on the Gsm8k using the LLaMA-7B model and an absolute accuracy increase of 5.2 points on the BBH evaluation benchmark with the LLaMA-65B model.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationACL 2025
EditorsWanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
PublisherAssociation for Computational Linguistics (ACL)
Pages8506-8524
Number of pages19
ISBN (Electronic)9798891762565
DOIs
StatePublished - 2025
Externally publishedYes
Event63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 - Vienna, Austria
Duration: 27 Jul 20251 Aug 2025

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Country/TerritoryAustria
CityVienna
Period27/07/251/08/25

Fingerprint

Dive into the research topics of 'ALW: Adaptive Layer-Wise contrastive decoding enhancing reasoning ability in Large Language Models'. Together they form a unique fingerprint.

Cite this