EMNLP 2024finding0 citations

Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses

Hung-Ting Su, Ya-Ching Hsu, Xudong Lin, Xiang-Qian Shi, Yulei Niu, Han-Yuan Hsu, Hung-yi Lee, Winston H. Hsu

Abstract

Large language models (LLMs) equipped with chain-of-thoughts (CoT) prompting have shown significant multi-step reasoning capabilities in factual content like mathematics, commonsense, and logic. However, their performance in narrative reasoning, which demands greater abstraction capabilities, remains unexplored. This study utilizes tropes in movie synopses to assess the abstract reasoning abilities of state-of-the-art LLMs and uncovers their low performance. We introduce a trope-wise querying approach to address these challenges and boost the F1 score by 11.8 points. Moreover, while prior studies suggest that CoT enhances multi-step reasoning, this study shows CoT can cause hallucinations in narrative content, reducing GPT-4’s performance. We also introduce an Adversarial Injection method to embed trope-related text tokens into movie synopses without explicit tropes, revealing CoT’s heightened sensitivity to such injections. Our comprehensive analysis provides insights for future research directions.

BibTeX
@inproceedings{su-etal-2024-unveiling,
    title = "Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses",
    author = "Su, Hung-Ting  and
      Hsu, Ya-Ching  and
      Lin, Xudong  and
      Shi, Xiang-Qian  and
      Niu, Yulei  and
      Hsu, Han-Yuan  and
      Lee, Hung-yi  and
      Hsu, Winston H.",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.872/",
    doi = "10.18653/v1/2024.findings-emnlp.872",
    pages = "14839--14854"
}
Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses · EMNLP 2024