@inproceedings{li-etal-2024-calibrating,
    title = "Calibrating {LLM}s with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring",
    author = "Li, Jiazheng  and
      Xu, Hainiu  and
      Sun, Zhaoyue  and
      Zhou, Yuxiang  and
      West, David  and
      Aloisi, Cesare  and
      He, Yulan",
    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://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.findings-emnlp.313/",
    doi = "10.18653/v1/2024.findings-emnlp.313",
    pages = "5452--5479",
    abstract = "Generating rationales that justify scoring decisions has been a promising way to facilitate explainability in automated scoring systems. However, existing methods do not match the accuracy of classifier-based methods. Plus, the generated rationales often contain hallucinated information. To address these issues, we propose a novel framework capable of generating more faithful rationales and, more importantly, matching performance with classifier-based black-box scoring systems. We first mimic the human assessment process by querying Large Language Models (LLMs) to generate a thought tree. We then summarise intermediate assessment decisions from each thought tree path for creating synthetic rationale data and rationale preference data. Finally, we utilise the generated synthetic data to calibrate LLMs through a two-step training process: supervised fine-tuning and preference optimization. Extensive experimental results demonstrate that our framework achieves a 38{\%} assessment performance improvement in the QWK score compared to prior work while producing higher-quality rationales, as recognised by human evaluators and LLMs. Our work sheds light on the effectiveness of performing preference optimization using synthetic preference data obtained from thought tree paths. Data and code are available at: https://github.com/lijiazheng99/thought{\_}tree{\_}assessment."
}