COLING 2025main2 citations

Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in LLMs

Nazanin Shafiabadi, Guillaume Wisniewski

Abstract

Many studies have explored when and how LLMs learn to use specific words, primarily by examining their learning curves. While these curves capture a model’s capacity to use words correctly in context, they often neglect the equally important skill of avoiding incorrect usage. In this paper, we introduce a new metric, anti-surprisal, which measures a model’s capacity to refrain from using words in inappropriate or unexpected contexts. By examining both correct usage and error avoidance, we offer a more comprehensive perspective on the learning dynamics of LLMs.

BibTeX
@inproceedings{shafiabadi-wisniewski-2025-beyond,
    title = "Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in {LLM}s",
    author = "Shafiabadi, Nazanin  and
      Wisniewski, Guillaume",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-main.443/",
    pages = "6636--6641"
}
Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in LLMs · COLING 2025