COLING 2024main9 citations

Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons

Shijia Zhou, Leonie Weissweiler, Taiqi He, Hinrich Schütze, David R. Mortensen, Lori Levin

Abstract

In this paper, we make a contribution that can be understood from two perspectives: from an NLP perspective, we introduce a small challenge dataset for NLI with large lexical overlap, which minimises the possibility of models discerning entailment solely based on token distinctions, and show that GPT-4 and Llama 2 fail it with strong bias. We then create further challenging sub-tasks in an effort to explain this failure. From a Computational Linguistics perspective, we identify a group of constructions with three classes of adjectives which cannot be distinguished by surface features. This enables us to probe for LLM’s understanding of these constructions in various ways, and we find that they fail in a variety of ways to distinguish between them, suggesting that they don’t adequately represent their meaning or capture the lexical properties of phrasal heads.

BibTeX
@inproceedings{zhou-etal-2024-constructions,
    title = "Constructions Are So Difficult That {E}ven Large Language Models Get Them Right for the Wrong Reasons",
    author = {Zhou, Shijia  and
      Weissweiler, Leonie  and
      He, Taiqi  and
      Sch{\"u}tze, Hinrich  and
      Mortensen, David R.  and
      Levin, Lori},
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.336/",
    pages = "3804--3811"
}
Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons · COLING 2024