作者位次 #2/4ACL 2026Poster· Natural Language Processing
Uncovering Sentiment Analysis Circuit in Large Language Model
Shichen Li · Zhouyang Wang · Zhongqing Wang · Peifeng Li
摘要
Large Language Models (LLMs) can perform sentiment analysis via natural language instructions, yet their predictions are highly sensitive to prompt phrasing. Prior work has shown that sentiment is encoded linearly in LLM representations, but the model’s ability to utilize this information remains...