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

arXiv: https://arxiv.org/abs/2404.03414 · HTML: https://mlsanity.com/paper/2404.03414/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step](https://mlsanity.com/paper/2306.14050/) (2023)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023)
- [ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness](https://mlsanity.com/paper/2304.10703/) (2023)
- [Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales](https://mlsanity.com/paper/2305.07095/) (2023)
- [Sci-CoT: Leveraging Large Language Models for Enhanced Knowledge Distillation in Small Models for Scientific QA](https://mlsanity.com/paper/2308.04679/) (2023)

## Built on by (most cited first, 12 of 12)

- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [Communicating Activations Between Language Model Agents](https://mlsanity.com/paper/2501.14082/) (2025)
- [A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness](https://mlsanity.com/paper/2510.13890/) (2025)
- [Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More](https://mlsanity.com/paper/2503.10542/) (2025)
- [Menta: A Small Language Model for On-Device Mental Health Prediction](https://mlsanity.com/paper/2512.02716/) (2025)
- [Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)](https://mlsanity.com/paper/2501.05465/) (2025)
- [When LLMs Team Up: The Emergence of Collaborative Affective Computing](https://mlsanity.com/paper/2506.01698/) (2025)
- [Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuning](https://mlsanity.com/paper/2509.07768/) (2025)
- [It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches](https://mlsanity.com/paper/2607.16205/) (2026)
- [SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation](https://mlsanity.com/paper/2505.00831/) (2025)

## Abstract (arXiv)

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.