@inproceedings{sun-etal-2025-interpret,
    title = "Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings",
    author = "Sun, Chenghao  and
      Huang, Zhen  and
      Zhang, Yonggang  and
      Lu, Le  and
      Li, Houqiang  and
      Tian, Xinmei  and
      Shen, Xu  and
      Ye, Jieping",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.196/",
    pages = "3873--3895",
    ISBN = "979-8-89176-251-0",
    abstract = "Large language models (LLMs) excel at downstream NLP tasks through in-context learning (ICL) with a few demonstrations of input{--}label pairs. However, the internal mechanisms behind ICL remain under-explored, particularly the mappings between inputs and labels. In this work, we reverse-engineer ICL by examining input-label mappings: what they are within LLMs, where they function, and how LLMs utilize them. (1) what: We discover input-label mappings stored within a few specific layers in the form of principal components (PCs), which capture human-interpretable and task-related words. (2) where: We propose a PC patching approach to identify the modules where input-label mappings function. Specifically, PC patching automatically crafts counterfactual representations using identified semantic PCs, rather than manually designing counterfactual text, to suppress the behavior related to LLM capability for ICL-related modules. Utilizing PC patching, we identify LLMs apply input-label mappings in a small fraction of attention heads. (3) how: We observe and verify that the identified key heads utilize input-label mappings from demonstrations to generate target labels for new queries. Based on these discoveries, we further show that precisely fine-tuning key ICL-related modules leads to significant improvements across diverse tasks."
}