Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought

Jooyoung Lee, Fan Yang, Thanh Tran, Qian Hu, Emre Barut, Kai-Wei Chang


Abstract
We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks. Specifically, the lightweight LM first generates a rationale for each input instance. The Frozen large LM is then prompted to predict a task output based on the rationale generated by the lightweight LM. Our approach is resource-efficient in the sense that it only requires training the lightweight LM. We optimize the model through 1) knowledge distillation and 2) reinforcement learning from rationale-oriented and task-oriented reward signals. We assess our method with multi-hop extractive question answering (QA) benchmarks, HotpotQA, and 2WikiMultiHopQA. Experimental results show that our approach outperforms all baselines regarding answer prediction accuracy. We also find that reinforcement learning helps the model to produce higher-quality rationales with improved QA performance.
Anthology ID:
2024.lrec-main.252
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:
2835–2843
Language:
URL:
https://aclanthology.org/2024.lrec-main.252
DOI:
Bibkey:
Cite (ACL):
Jooyoung Lee, Fan Yang, Thanh Tran, Qian Hu, Emre Barut, and Kai-Wei Chang. 2024. Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2835–2843, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought (Lee et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.252.pdf