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, and Chengwei Su, in LREC-COLING, 2024.

Download the full text

Abstract

We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) 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.

Bib Entry

@inproceedings{lee2024small,
  title = {Can small language models help large language models reason better?: LM-guided chain-of-thought},
  author = {Lee, Jooyoung and Yang, Fan and Tran, Thanh and Hu, Qian and Barut, Emre and Chang, Kai-Wei and Su, Chengwei},
  year = {2024},
  booktitle = {LREC-COLING}
}