# Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models

arXiv: https://arxiv.org/abs/2405.00402 · HTML: https://mlsanity.com/paper/2405.00402/

## Key facts

- Cited by 24 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 31 of its 45 references that are in the map.
- First posted on arXiv 1 May 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification](https://mlsanity.com/paper/2308.07921/) (2023)
- [Making Large Language Models Better Reasoners with Alignment](https://mlsanity.com/paper/2309.02144/) (2023)

## Built on by (most cited first, 24 of 24)

- [GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices](https://mlsanity.com/paper/2406.08451/) (2024)
- [Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://mlsanity.com/paper/2503.05179/) (2025)
- [OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System](https://mlsanity.com/paper/2509.18091/) (2025)
- [Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions](https://mlsanity.com/paper/2502.12616/) (2025)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL](https://mlsanity.com/paper/2504.15077/) (2025)
- [Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs](https://mlsanity.com/paper/2407.03181/) (2024)
- [Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment](https://mlsanity.com/paper/2502.07803/) (2025)
- [Self-Training Large Language Models with Confident Reasoning](https://mlsanity.com/paper/2505.17454/) (2025)
- [ProRefine: Inference-Time Prompt Refinement with Textual Feedback](https://mlsanity.com/paper/2506.05305/) (2025)
- [DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning](https://mlsanity.com/paper/2505.15734/) (2025)
- [Making, not Taking, the Best of N](https://mlsanity.com/paper/2510.00931/) (2025)
- [Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations](https://mlsanity.com/paper/2410.22874/) (2024)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark](https://mlsanity.com/paper/2505.17021/) (2025)
- [CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning](https://mlsanity.com/paper/2507.00045/) (2025)
- [DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning](https://mlsanity.com/paper/2510.15050/) (2025)
- [Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models](https://mlsanity.com/paper/2603.13985/) (2026)
- [Aligning VLM Assistants with Personalized Situated Cognition](https://mlsanity.com/paper/2506.00930/) (2025)
- [Enhancing XAI Narratives through Multi-Narrative Refinement and Knowledge Distillation](https://mlsanity.com/paper/2510.03134/) (2025)
- [MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning](https://mlsanity.com/paper/2508.21451/) (2025)
- [GIER: Gap-Driven Self-Refinement for Large Language Models](https://mlsanity.com/paper/2509.00325/) (2025)
- [Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series](https://mlsanity.com/paper/2511.01354/) (2025)
- [GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs](https://mlsanity.com/paper/2511.13007/) (2025)

## Abstract (arXiv)

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches deliver more performant models, they do not show sufficiently strong generalization ability as the training only relies on the provided demonstrations. In this paper, we propose the Self-refine Instruction-tuning method that elicits Smaller Language Models to self-refine their abilities. Our approach is based on a two-stage process, where reasoning abilities are first transferred between LLMs and Small Language Models (SLMs) via Instruction-tuning on demonstrations provided by LLMs, and then the instructed models Self-refine their abilities through preference optimization strategies. In particular, the second phase operates refinement heuristics based on the Direct Preference Optimization algorithm, where the SLMs are elicited to deliver a series of reasoning paths by automatically sampling the generated responses and providing rewards using ground truths from the LLMs. Results obtained on commonsense and math reasoning tasks show that this approach significantly outperforms Instruction-tuning in both in-domain and out-domain scenarios, aligning the reasoning abilities of Smaller and Larger Language Models.