一作ICLR 2026Poster· Deep Learning / Everything Else
SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs
Boyi Deng · Yu Wan · Baosong Yang · Fei Huang · Wenjie Wang · Fuli Feng
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Boyi Deng · Yu Wan · Baosong Yang · Fei Huang · Wenjie Wang · Fuli Feng
Yi Fang · Wenjie Wang · Mingfeng Xue · Boyi Deng · Fengli Xu · Dayiheng Liu · Fuli Feng
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...