Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models

2026 Open access

Read full text
Authors: Ruixue Deng, Xiaoyang Hu, Miles Gilberti, Shane Storks, Aman Taxali, Mike Angstadt, Chandra Sripada, Joyce Yue Chai
DOI: 10.18653/v1/2026.acl-long.155
Cited by: 0

Abstract

Ruixuan Deng, Xiaoyang Hu, Miles Gilberti, Shane Storks, Aman Taxali, Mike Angstadt, Chandra Sripada, Joyce Chai. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Fields of Study & Subjects

Topic Modeling Computational and Text Analysis Methods Explainable Artificial Intelligence (XAI)

Publication details

Pages
3419–3451
Publication date
1 January 2026
Language
EN