# Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning

arXiv: https://arxiv.org/abs/2403.20046 · HTML: https://mlsanity.com/paper/2403.20046/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Pretraining Language Models with Human Preferences](https://mlsanity.com/paper/2302.08582/) (2023)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [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)
- [Learning From Mistakes Makes LLM Better Reasoner](https://mlsanity.com/paper/2310.20689/) (2023)
- [CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge](https://mlsanity.com/paper/2109.01653/) (2021)
- [QED: A Framework and Dataset for Explanations in Question Answering](https://mlsanity.com/paper/2009.06354/) (2020)
- [Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation](https://mlsanity.com/paper/1906.00363/) (2019)

## Built on by (most cited first, 30 of 70)

- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [A Survey on Self-Evolution of Large Language Models](https://mlsanity.com/paper/2404.14387/) (2024)
- [Visual Agents as Fast and Slow Thinkers](https://mlsanity.com/paper/2408.08862/) (2024)
- [Internal Consistency and Self-Feedback in Large Language Models: A Survey](https://mlsanity.com/paper/2407.14507/) (2024)
- [DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature](https://mlsanity.com/paper/2405.04819/) (2024)
- [Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?](https://mlsanity.com/paper/2506.21215/) (2025)
- [TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review](https://mlsanity.com/paper/2506.07642/) (2025)
- [SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents](https://mlsanity.com/paper/2411.03284/) (2024)
- [DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models](https://mlsanity.com/paper/2505.13975/) (2025)
- [Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models](https://mlsanity.com/paper/2502.04404/) (2025)
- [Exploring Large Language Models for Feature Selection: A Data-centric Perspective](https://mlsanity.com/paper/2408.12025/) (2024)
- [Entropy-Gated Branching for Efficient Test-Time Reasoning](https://mlsanity.com/paper/2503.21961/) (2025)
- [LEMMA: Learning from Errors for MatheMatical Advancement in LLMs](https://mlsanity.com/paper/2503.17439/) (2025)
- [On the Fundamental Limits of LLMs at Scale](https://mlsanity.com/paper/2511.12869/) (2025)
- [Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary](https://mlsanity.com/paper/2505.18325/) (2025)
- [M-IFEval: Multilingual Instruction-Following Evaluation](https://mlsanity.com/paper/2502.04688/) (2025)
- [Optimizing Language Model's Reasoning Abilities with Weak Supervision](https://mlsanity.com/paper/2405.04086/) (2024)
- [Reasoning Elicitation in Language Models via Counterfactual Feedback](https://mlsanity.com/paper/2410.03767/) (2024)
- [No Need for Explanations: LLMs can implicitly learn from mistakes in-context](https://mlsanity.com/paper/2502.08550/) (2025)
- [Learning from Diverse Reasoning Paths with Routing and Collaboration](https://mlsanity.com/paper/2508.16861/) (2025)
- [LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement](https://mlsanity.com/paper/2407.00497/) (2024)
- [Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information](https://mlsanity.com/paper/2410.04463/) (2024)
- [Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation](https://mlsanity.com/paper/2605.09253/) (2026)
- [E2CL: Exploration-based Error Correction Learning for Embodied Agents](https://mlsanity.com/paper/2409.03256/) (2024)
- [Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem](https://mlsanity.com/paper/2409.07123/) (2024)
- [Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models](https://mlsanity.com/paper/2410.01795/) (2024)
- [Can foundation models actively gather information in interactive environments to test hypotheses?](https://mlsanity.com/paper/2412.06438/) (2024)
- [Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models](https://mlsanity.com/paper/2408.08210/) (2024)

## Abstract (arXiv)

Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While humans can indeed imitate correct examples, learning from our mistakes is another vital aspect of human cognition. Hence, a question naturally arises: textitcan LLMs learn and benefit from their mistakes, especially for their reasoning?  This study investigates this problem from both the prompting and model-tuning perspectives. We begin by introducing textscCoTErrorSet, a new benchmark with 609,432 questions, each designed with both correct and error references, and demonstrating the types and reasons for making such mistakes. To explore the effectiveness of those mistakes, we design two methods: (1) Self-rethinking prompting guides LLMs to rethink whether they have made similar previous mistakes; and (2) Mistake tuning involves finetuning models in both correct and incorrect reasoning domains, rather than only tuning models to learn ground truth in traditional methodology. We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions. Our two methods offer potentially cost-effective strategies by leveraging errors to enhance reasoning capabilities, which costs significantly less than creating meticulously hand-crafted golden references. We ultimately make a thorough analysis of the reasons behind LLMs' errors, which provides directions that future research needs to overcome. textscCoTErrorSet will be published soon on texttturlhttps://github.com/YookiTong/Learn-from-Mistakes-CotErrorSet.