Abstract
Chain-of-thought (CoT) advances the reasoning abilities of large language models (LLMs) and achieves superior performance in complex reasoning tasks. However, most CoT studies rely on carefully designed human-annotated rational chains to prompt LLMs, posing challenges for real-world applications where labeled data is available without rational chains. This paper proposes a new strategy, AutomateCoT (Automatic Prompt Augmentation and Selection with Chain-of-Thought), that can bypass human engineering of CoT by automatically augmenting rational chains from a small labeled dataset, and then pruning low-quality chains to construct a candidate pool of machinegenerated rationale chains based on the labels. Finally, it selects the optimal combination of several rationale chains from the pool for CoT prompting by employing a variance-reduced policy gradient strategy to estimate the significance of each example. Automate-CoT enables a quick adaptation of the CoT technique to different tasks. Experimental results demonstrate the effectiveness of our method, where competitive results are achieved on arithmetic reasoning (+2.7%), commonsense reasoning (+3.4%), symbolic reasoning (+3.2%), and non-reasoning tasks (+2.5%).- Anthology ID:
- 2023.findings-emnlp.811
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12113–12139
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.811
- DOI:
- 10.18653/v1/2023.findings-emnlp.811
- Cite (ACL):
- Kashun Shum, Shizhe Diao, and Tong Zhang. 2023. Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12113–12139, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data (Shum et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-emnlp.811.pdf