C3oT: Generating Shorter Chain-of-Thought Without Compromising Effectiveness
Top Cited Papers
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 24312-24320
Abstract
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.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression2024
- Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling2024
- Learning to Compress Prompts with Gist Tokens2023
- Adapting Language Models to Compress Contexts2023
- Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models2022
- Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models2022
- Few-Shot Self-Rationalization with Natural Language Prompts2022
- AdapLeR: Speeding up Inference by Adaptive Length Reduction2022
- Did Aristotle Use a Laptop?A Question Answering Benchmark with Implicit Reasoning StrategiesTransactions of the Association for Computational Linguistics, 2021
- MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms2019