RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners

Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, Jingbo Zhu


Abstract
Large Language Models (LLMs) have achieved impressive performance across various reasoning tasks. However, even state-of-the-art LLMs such as ChatGPT are prone to logical errors during their reasoning processes. Existing solutions, such as deploying task-specific verifiers or voting over multiple reasoning paths, either require extensive human annotations or fail in scenarios with inconsistent responses. To address these challenges, we introduce RankPrompt, a new prompting method that enables LLMs to self-rank their responses without additional resources. RankPrompt breaks down the ranking problem into a series of comparisons among diverse responses, leveraging the inherent capabilities of LLMs to generate chains of comparison as contextual exemplars. Our experiments across 11 arithmetic and commonsense reasoning tasks show that RankPrompt significantly enhances the reasoning performance of ChatGPT and GPT-4, with improvements of up to 13%. Moreover, RankPrompt excels in LLM-based automatic evaluations for open-ended tasks, aligning with human judgments 74% of the time in the AlpacaEval dataset. It also exhibits robustness to variations in response order and consistency. Collectively, our results validate RankPrompt as an effective method for eliciting high-quality feedback from language models.
Anthology ID:
2024.lrec-main.1183
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
13524–13536
Language:
URL:
https://aclanthology.org/2024.lrec-main.1183
DOI:
Bibkey:
Cite (ACL):
Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, and Jingbo Zhu. 2024. RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13524–13536, Torino, Italia. ELRA and ICCL.
Cite (Informal):
RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (Hu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1183.pdf