Predicting Text Preference Via Structured Comparative Reasoning

Jing Nathan Yan, Tianqi Liu, Justin T Chiu, Jiaming Shen, Zhen Qin, Yue Yu, Yao Zhao, Charumathi Lakshmanan, Yair Kurzion, Alexander M Rush, Jialu Liu, Michael Bendersky

Abstract: Comparative reasoning plays a crucial role in predicting text preferences; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning, leading to incorrect preference predictions. While approaches like Chain-of-Thought improve accuracy in many settings, they struggle to consistently distinguish the similarities and differences of complex texts. We introduce SC^2, a modelthat prompts LLMs to predict text preferences by generating structured intermediate comparisons. SC2 begins by proposing aspects for comparison, followed by generating textual comparisons under each aspect. We select consistent comparisons with a pairwise comparator that ensures each comparison of a given aspect clearly distinguishes differences between texts, significantly reducing hallucination and improving consistency. Our empirical studies across various NLP tasks, including summarization, retrieval, and automatic rating, demonstrate that SC^2’s enhanced performance in text preference prediction is significant.