mlsanityData to 7 Oct 2026

Learning From Correctness Without Prompting Makes LLM Efficient Reasoner

arXiv 2403.19094 ↗First posted 28 Mar 2024cs.CLcited by 15

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content. One potential approach to mitigate these issues is learning from human or external feedback (e.g. tools). In this paper, we introduce an intrinsic self-correct reasoning framework for LLMs that eliminates the need for human feedback, external tools, and handcraft prompts. The proposed framework, based on a multi-step reasoning paradigm Learning from Correctness (textscLeCo), improves reasoning performance without needing to learn from errors. This paradigm prioritizes learning from correct reasoning steps, and a unique method to measure confidence for each reasoning step based on generation logits. Experimental results across various multi-step reasoning tasks demonstrate the effectiveness of the framework in improving reasoning performance with reduced token consumption.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 32 of its 64 references that are in the map. First posted on arXiv 28 Mar 2024.

Builds on

32 of 64 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  2. 2023Contrastive Decoding Improves Reasoning in Large Language Models17 Sep
  3. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies6 Aug
  4. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  5. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2023Let's Verify Step by Stepcited by 3,598
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  9. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  10. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  11. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  12. 2023Instruction Tuning with GPT-4cited by 676
15 more
  1. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  2. 2023Textbooks Are All You Needcited by 561
  3. 2023Orca: Progressive Learning from Complex Explanation Traces of GPT-4cited by 369
  4. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  5. 2023Faithful Chain-of-Thought Reasoningcited by 285
  6. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  7. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 226
  8. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  9. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  10. 2023Large Language Models as Analogical Reasonerscited by 107
  11. 2023Learning From Mistakes Makes LLM Better Reasonercited by 97
  12. 2024Tuning Language Models by Proxycited by 88
  13. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  14. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generationcited by 55
  15. 2023DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 6; 2026: 3.

15 papers.

Sort:

By area:

  1. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  2. 2024Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoningcited by 50
  3. 2024Process-Driven Autoformalization in Lean 4cited by 45
  4. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraintscited by 34
  5. 2024MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMscited by 30
  6. 2024EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimizationcited by 28
  7. 2024AutoPSV: Automated Process-Supervised Verifiercited by 28
  8. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 18
  9. 2025A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematicscited by 11
  10. 2025Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Stepscited by 9
  11. 2025Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generationcited by 5
  12. 2025A Survey of Deep Learning for Geometry Problem Solvingcited by 4
3 more
  1. 2026Believe Your Model: Distribution-Guided Confidence Calibrationcited by 2
  2. 2026Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attributioncited by 2
  3. 2026Evaluating the Relevance of Uncertainty Estimators for LLM Hallucinationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
  2. 2024LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
  3. 2024Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving
  4. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
  5. 2022Large Language Models Can Self-Improve
  6. 2025Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
  7. 2025From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs
  8. 2025Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique