mlsanityData to 7 Oct 2026

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

arXiv 2308.09583 ↗First posted 18 Aug 2023cs.CL cs.AI cs.LGcited by 618

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, most existing open-source models are only pre-trained on large-scale internet data and without math-related optimization. In this paper, we present WizardMath, which enhances the mathematical CoT reasoning abilities of LLMs without using external python tools, by applying our proposed Reinforcement Learning from Evol-Instruct Feedback (RLEIF) method to the domain of math. Through extensive experiments on two mathematical reasoning benchmarks, namely GSM8k and MATH, we reveal the extraordinary capabilities of our model. Remarkably, WizardMath-Mistral 7B surpasses top-tier open-source LLMs by a substantial margin with higher data efficiency. Furthermore, WizardMath 70B even outperforms GPT-3.5-Turbo, Claude 2, Gemini Pro and GPT-4-early-version. Additionally, our preliminary exploration highlights the pivotal role of instruction evolution and process supervision in achieving exceptional math performance. For more details refer to https://github.com/nlpxucan/WizardLM

Key facts. Cited by 618 papers in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 80 of its 153 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

80 of 153 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Scaling Relationship on Learning Mathematical Reasoning with Large Language Models3 Aug
  2. 2023How well do Large Language Models perform in Arithmetic tasks?16 Mar
  3. 2023MathPrompter: Mathematical Reasoning using Large Language Models4 Mar
  4. 2022A Survey of Deep Learning for Mathematical Reasoning20 Dec
  5. 2022Solving Math Word Problems via Cooperative Reasoning induced Language Models28 Oct
  6. 2022Solving Quantitative Reasoning Problems with Language Models29 Jun
  7. 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions28 May
  8. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction19 Mar

Other references · 72

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  9. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  10. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  11. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  12. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
38 more
  1. 2023Let's Verify Step by Stepcited by 3,598
  2. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  6. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  8. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  9. 2020Learning to summarize from human feedbackcited by 2,562
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  11. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  12. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  13. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  14. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  15. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  16. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  17. 2023PaLM 2 Technical Reportcited by 1,154
  18. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  19. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  20. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  21. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  22. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  23. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  24. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  25. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  26. 2023StarCoder: may the source be with you!cited by 790
  27. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
  28. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  29. 2022Galactica: A Large Language Model for Sciencecited by 736
  30. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  31. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  32. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
  33. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  34. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  35. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  36. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  37. 2014Neural Turing Machinescited by 630
  38. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 53; 2024: 262; 2025: 205; 2026: 98.

618 papers.

Sort:

By area:

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2023Qwen Technical Reportcited by 3,273
  3. 2025s1: Simple test-time scalingcited by 1,311
  4. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 951
  5. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  6. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  7. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 679
  8. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 621
  9. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  10. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  11. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  12. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 480
38 more
  1. 2023Llemma: An Open Language Model For Mathematicscited by 385
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  4. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  5. 2024LoRA Learns Less and Forgets Lesscited by 313
  6. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  7. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  8. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 292
  9. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 292
  10. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  11. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  12. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 283
  13. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  14. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  15. 2024Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMscited by 265
  16. 2024PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Modelscited by 261
  17. 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMscited by 257
  18. 2024Iterative Reasoning Preference Optimizationcited by 244
  19. 2024On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Surveycited by 240
  20. 2024ReFT: Reasoning with Reinforced Fine-Tuningcited by 236
  21. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  22. 2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Modelcited by 208
  23. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 191
  24. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyondcited by 175
  25. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
  26. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 158
  27. 2024Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8Bcited by 156
  28. 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoningcited by 155
  29. 2024GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solverscited by 155
  30. 2024Orca-Math: Unlocking the potential of SLMs in Grade School Mathcited by 151
  31. 2024MathScale: Scaling Instruction Tuning for Mathematical Reasoningcited by 144
  32. 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 144
  33. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  34. 2024MAmmoTH2: Scaling Instructions from the Webcited by 143
  35. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scalingcited by 135
  36. 2024Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Modelscited by 133
  37. 2025Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Stepcited by 130
  38. 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questionscited by 129

50 most cited of 618 All 618 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models
  2. 2025A Survey on Large Language Models for Mathematical Reasoning
  3. 2023MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
  4. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Example
  5. 2025LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
  6. 2026PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning
  7. 2025Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
  8. 2025Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning