# Small Language Model Can Self-correct

arXiv: https://arxiv.org/abs/2401.07301 · HTML: https://mlsanity.com/paper/2401.07301/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 33 references that are in the map.
- First posted on arXiv 14 Jan 2024.

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

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://mlsanity.com/paper/2307.11019/) (2023)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation](https://mlsanity.com/paper/2306.05783/) (2023)

## Built on by (most cited first, 23 of 23)

- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Small Language Models Need Strong Verifiers to Self-Correct Reasoning](https://mlsanity.com/paper/2404.17140/) (2024)
- [Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions](https://mlsanity.com/paper/2410.02584/) (2024)
- [Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs](https://mlsanity.com/paper/2412.19513/) (2024)
- [Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience](https://mlsanity.com/paper/2404.10315/) (2024)
- [LEMMA: Learning from Errors for MatheMatical Advancement in LLMs](https://mlsanity.com/paper/2503.17439/) (2025)
- [Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement](https://mlsanity.com/paper/2506.01663/) (2025)
- [ProgCo: Program Helps Self-Correction of Large Language Models](https://mlsanity.com/paper/2501.01264/) (2025)
- [Lightweight LLM Agent Memory with Small Language Models](https://mlsanity.com/paper/2604.07798/) (2026)
- [Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models](https://mlsanity.com/paper/2504.18116/) (2025)
- [Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection](https://mlsanity.com/paper/2403.14238/) (2024)
- [Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models](https://mlsanity.com/paper/2410.13413/) (2024)
- [Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models](https://mlsanity.com/paper/2504.02902/) (2025)
- [Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future](https://mlsanity.com/paper/2604.27924/) (2026)
- [SED: Self-Evaluation Decoding Enhances Large Language Models for Better Generation](https://mlsanity.com/paper/2405.16552/) (2024)
- [Self-Correcting Code Generation Using Small Language Models](https://mlsanity.com/paper/2505.23060/) (2025)
- [A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models](https://mlsanity.com/paper/2508.12903/) (2025)
- [Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations](https://mlsanity.com/paper/2505.18466/) (2025)
- [Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs](https://mlsanity.com/paper/2509.00096/) (2025)
- [Efficient LLM Safety Evaluation through Multi-Agent Debate](https://mlsanity.com/paper/2511.06396/) (2025)
- [HITgram: A Platform for Experimenting with n-gram Language Models](https://mlsanity.com/paper/2412.10717/) (2024)
- [Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games](https://mlsanity.com/paper/2506.23626/) (2025)
- [Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models](https://mlsanity.com/paper/2509.01350/) (2025)

## Abstract (arXiv)

Generative Language Models (LMs) such as ChatGPT have exhibited remarkable performance across various downstream tasks. Nevertheless, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. Previous studies have devised sophisticated pipelines and prompts to induce large LMs to exhibit the capability for self-correction. However, large LMs are explicitly prompted to verify and modify its answers separately rather than completing all steps spontaneously like humans. Moreover, these complex prompts are extremely challenging for small LMs to follow. In this paper, we introduce the underlineIntrinsic underlineSelf-underlineCorrection (ISC) in generative language models, aiming to correct the initial output of LMs in a self-triggered manner, even for those small LMs with 6 billion parameters. Specifically, we devise a pipeline for constructing self-correction data and propose Partial Answer Masking (PAM), aiming to endow the model with the capability for intrinsic self-correction through fine-tuning. We conduct experiments using LMs with parameters sizes ranging from 6 billion to 13 billion in two tasks, including commonsense reasoning and factual knowledge reasoning. Our experiments demonstrate that the outputs generated using ISC outperform those generated without self-correction. We believe that the output quality of even small LMs can be further improved by empowering them with the ability to intrinsic self-correct.