# ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting

arXiv: https://arxiv.org/abs/2403.14312 · HTML: https://mlsanity.com/paper/2403.14312/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 52 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)

## Built on by (most cited first, 8 of 8)

- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents](https://mlsanity.com/paper/2505.10961/) (2025)
- [Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding](https://mlsanity.com/paper/2603.04977/) (2026)
- [Hybrid LLM/Rule-based Approaches to Business Insights Generation from Structured Data](https://mlsanity.com/paper/2404.15604/) (2024)
- [Irony Detection, Reasoning and Understanding in Zero-shot Learning](https://mlsanity.com/paper/2501.16884/) (2025)
- [SafeCoT: Improving VLM Safety with Minimal Reasoning](https://mlsanity.com/paper/2506.08399/) (2025)
- [CAP: Controllable Alignment Prompting for Unlearning in LLMs](https://mlsanity.com/paper/2604.21251/) (2026)
- [PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning](https://mlsanity.com/paper/2507.18857/) (2025)

## Abstract (arXiv)

Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning tasks. Existing CoT synthesis approaches usually focus on simpler reasoning tasks and thus result in low-quality and inconsistent CoT prompts. In response to this challenge, we present an empirical investigation of CoT prompting and introduce CoTGenius, a novel framework designed for the automatic generation of superior CoT prompts. CoTGenius is developed based on three major evolution strategies, i.e., complicate, diversify, and specify-alongside two filtering mechanisms: evolutionary success judgement and correctness verification. We further employ CoTGenius to create an extensive CoT dataset, and subsequently fine-tune the Llama 2-Chat 7B and 13B models on this dataset. We call the resulting model ChainLM. To deal with the cumulative error issue in reasoning steps, we propose a step-level debating method, wherein multiple debaters discuss each reasoning step to arrive at the correct answer. Extensive experiments demonstrate that our ChainLM models exhibit enhanced proficiency in addressing a spectrum of complex reasoning problems compared to existing models. In addition, we conduct an in-depth analysis of the impact of data categories within CoTGenius on the model performance. We release our dataset and code at https://github.com/RUCAIBox/ChainLM.