@inproceedings{yuan-etal-2025-exploiting,
    title = "Exploiting Contextual Knowledge in {LLM}s through $\mathcal{V}$-usable Information based Layer Enhancement",
    author = "Yuan, Xiaowei  and
      Yang, Zhao  and
      Huang, Ziyang  and
      Wang, Yequan  and
      Fan, Siqi  and
      Ju, Yiming  and
      Zhao, Jun  and
      Liu, Kang",
    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.1531/",
    pages = "31726--31741",
    ISBN = "979-8-89176-251-0",
    abstract = "Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet they often struggle with context-faithfulness generations that properly reflect contextual knowledge. While existing approaches focus on enhancing the decoding strategies, they ignore the fundamental mechanism of how contextual information is processed within LLMs' internal states. As a result, LLMs remain limited in their ability to fully leverage contextual knowledge. In this paper, we propose Context-aware Layer Enhancement (CaLE), a novel intervention method that enhances the utilization of contextual knowledge within LLMs' internal representations. By employing $\mathcal{V}$-usable information analysis, CaLE strategically amplifies the growth of contextual information at an optimal layer, thereby enriching representations in the final layer. Our experiments demonstrate that CaLE effectively improves context-faithful generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge."
}