C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (23) · 24312-24320
DOI: 10.1609/aaai.v39i23.34608 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yu Kang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref).
Abstract (Originalsprache)
Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the length of the generated CoT is much longer than the desired final answer, which results in additional decoding costs. Furthermore, existing research has discovered that shortening the reasoning steps in CoT, even while preserving the key information, diminishes LLMs' abilities. These phenomena make it difficult to use LLMs and CoT in many real-world applications that only require the final answer and are sensitive to latency, such as search and recommendation. To reduce the costs of model decoding and shorten the length of the generated CoT, this paper presents Conditioned Compressed Chain-of-Thought (C3oT), a CoT compression framework that involves a compressor to compress an original longer CoT into a shorter CoT while maintaining key information and interpretability, a conditioned training method to train LLMs with both longer CoT and shorter CoT simultaneously to learn the corresponding relationships between them, and a conditioned inference method to gain the reasoning ability learned from longer CoT by generating shorter CoT. We conduct experiments over four datasets from arithmetic and commonsense scenarios, showing that the proposed method is capable of compressing the length of generated CoT by up to more than 50% without compromising its effectiveness.
Zitieren
APA
Kang, Y., Sun, X., Chen, L., & Zou, W. (2025). C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness. Proceedings of the AAAI Conference on Artificial Intelligence, 39(23), 24312-24320. https://doi.org/10.1609/aaai.v39i23.34608
Vancouver
Kang Y, Sun X, Chen L, Zou W. C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(23):24312-24320. doi:10.1609/aaai.v39i23.34608
BibTeX
@article{Kang2025,
author = {Kang, Yu and Sun, Xianghui and Chen, Liangyu and Zou, Wei},
title = {C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {23},
pages = {24312--24320},
doi = {10.1609/aaai.v39i23.34608}
}
EUVIMED