mlsanityData to 14 Oct 2026

Making Large Language Models Better Reasoners with Step-Aware Verifier

arXiv 2206.02336 ↗First posted 6 Jun 2022cs.CL cs.AIcited by 233

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Diverse Verifier on Reasoning Step), a novel approach that further enhances the reasoning capability of language models. DIVERSE has three main components: first, it generates diverse prompts to explore different reasoning paths for the same question; second, it uses a verifier to filter out incorrect answers based on a weighted voting scheme; and third, it verifies each reasoning step individually instead of the whole chain. We evaluate DIVERSE on the latest language model code-davinci-002 and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks (e.g., GSM8K 74.4% to 83.2%).

Key facts. Cited by 233 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 56 of its 70 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

56 of 70 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning19 May
  2. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?25 Feb

Other references · 54

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  12. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
38 more
  1. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  2. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  3. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  4. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  5. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  6. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  7. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  8. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 872
  9. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  10. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  11. 2021MetaICL: Learning to Learn In Contextcited by 454
  12. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  13. 2016Solving General Arithmetic Word Problemscited by 360
  14. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  15. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  16. 2019Abductive Commonsense Reasoningcited by 301
  17. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
  18. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
  19. 2022Can language models learn from explanations in context?cited by 249
  20. 2020ReClor: A Reading Comprehension Dataset Requiring Logical Reasoningcited by 217
  21. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  22. 2020Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learningcited by 216
  23. 2021How Many Data Points is a Prompt Worth?cited by 198
  24. 2019CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Textcited by 162
  25. 2020Injecting Numerical Reasoning Skills into Language Modelscited by 133
  26. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  27. 2021A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Modelscited by 101
  28. 2021Generate & Rank: A Multi-task Framework for Math Word Problemscited by 82
  29. 2020Logic-Guided Data Augmentation and Regularization for Consistent Question Answeringcited by 78
  30. 2019Cognitive Graph for Multi-Hop Reading Comprehension at Scalecited by 65
  31. 2020Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Trackingcited by 65
  32. 2019Giving BERT a Calculator: Finding Operations and Arguments with Reading Comprehensioncited by 51
  33. 2018Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledgecited by 48
  34. 2018Improving Natural Language Inference Using External Knowledge in the Science Questions Domaincited by 48
  35. 2018Commonsense for Generative Multi-Hop Question Answering Taskscited by 48
  36. 2021Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Textcited by 46
  37. 2022Reasoning Like Program Executorscited by 45
  38. 2019A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoningcited by 41

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 52; 2024: 70; 2025: 88; 2026: 23.

233 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,576
  2. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  3. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 625
  4. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  5. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
  6. 2023Scaling Relationship on Learning Mathematical Reasoning with Large Language Modelscited by 427
  7. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  8. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 309
  9. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  10. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 290
  11. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 282
  12. 2024Token-Budget-Aware LLM Reasoningcited by 247
38 more
  1. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  3. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  4. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 223
  5. 2024V-STaR: Training Verifiers for Self-Taught Reasonerscited by 217
  6. 2023Universal Self-Consistency for Large Language Model Generationcited by 203
  7. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  8. 2024More Agents Is All You Needcited by 180
  9. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verificationcited by 166
  10. 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Designcited by 164
  11. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMscited by 163
  12. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  13. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 143
  14. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 137
  15. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoningcited by 119
  16. 2025Process Reward Models That Thinkcited by 118
  17. 2024ARGS: Alignment as Reward-Guided Searchcited by 103
  18. 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinementscited by 103
  19. 2023Learning From Mistakes Makes LLM Better Reasonercited by 101
  20. 2023Cumulative Reasoning with Large Language Modelscited by 94
  21. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 90
  22. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoningcited by 86
  23. 2023OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoningcited by 85
  24. 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Modelscited by 80
  25. 2024Process Reward Model with Q-Value Rankingscited by 80
  26. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Promptingcited by 77
  27. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  28. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  29. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoningcited by 69
  30. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chainscited by 65
  31. 2023Making Large Language Models Better Reasoners with Alignmentcited by 63
  32. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  33. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 63
  34. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 63
  35. 2023Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decodingcited by 60
  36. 2023Guiding Language Model Reasoning with Planning Tokenscited by 58
  37. 2023Do LLM Agents Exhibit Social Behavior?cited by 53
  38. 2025A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Futurecited by 53

50 most cited of 233 All 233 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Patience Is The Key to Large Language Model Reasoning
  2. 2025General-Reasoner: Advancing LLM Reasoning Across All Domains
  3. 2025Diversity-Aware Policy Optimization for Large Language Model Reasoning
  4. 2025Reinforcing General Reasoning without Verifiers
  5. 2026Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
  6. 2024Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems
  7. 2022Complexity-Based Prompting for Multi-Step Reasoning
  8. 2023Specializing Smaller Language Models towards Multi-Step Reasoning