一作ACL 2026Poster· Natural Language Processing
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
Yi Fang · Wenjie Wang · Mingfeng Xue · Boyi Deng · Fengli Xu · Dayiheng Liu · Fuli Feng
摘要
Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are autonomously selected by LRMs themselves. However, such autonomo...