Work

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models

Year: 2026

Type: conference-paper

Abstract: Dan Shi, Zhuowen Han, Simon Ostermann, Renren Jin, Josef Van Genabith, Deyi Xiong. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2026.acl-long.1808

Authors: Dan Shi, Zhuowen Han, Simon Ostermann, Renren Jin, Josef Van Genabith, Deyi Xiong

Institutions: Tianjin University, German Research Centre for Artificial Intelligence, Saarland University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: China Scholarship Council, National Key Research and Development Program of China

Award: G3721206413

OpenAlex ID: W7166880802

FWCI:

Cites:

Cited by:

Related to: 10