1
Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders
稀疏自编码器揭开LLM情感推理黑箱，找出哪些情绪更难被模型识别及其因果机制。
arXiv:2604.25866v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications,…