mlsanityData to 7 Oct 2026

Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning

arXiv 2401.17686 ↗First posted 31 Jan 2024cs.CLcited by 24

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Recent advancements have significantly augmented the reasoning capabilities of Large Language Models (LLMs) through various methodologies, especially chain-of-thought (CoT) reasoning. However, previous methods fail to address reasoning errors in intermediate steps, leading to accumulative errors. In this paper, we propose Deductive Beam Search (DBS), which seamlessly integrates CoT and deductive reasoning with step-wise beam search for LLMs. Our approach deploys a verifier, verifying the deducibility of a reasoning step and its premises, thus alleviating the error accumulation. Furthermore, we introduce a scalable and labor-free data construction method to amplify our model's verification capabilities. Extensive experiments demonstrate that our approach significantly enhances the base performance of LLMs of various scales (7B, 13B, 70B, and ChatGPT) across 8 reasoning datasets from 3 diverse reasoning genres, including arithmetic, commonsense, and symbolic. Moreover, our analysis proves DBS's capability of detecting diverse and subtle reasoning errors and robustness on different model scales.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 37 of its 54 references that are in the map. First posted on arXiv 31 Jan 2024.

Builds on

37 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning14 Nov
  2. 2023Cumulative Reasoning with Large Language Models8 Aug
  3. 2023Deductive Verification of Chain-of-Thought Reasoning6 Jun
  4. 2023PaLM 2 Technical Report17 May
  5. 2022Making Large Language Models Better Reasoners with Step-Aware Verifier6 Jun

Other references · 32

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2022Emergent Abilities of Large Language Modelscited by 2,483
  10. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  11. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  12. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
20 more
  1. 2018Hierarchical Neural Story Generationcited by 1,182
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  3. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  6. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  7. 2016Solving General Arithmetic Word Problemscited by 353
  8. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  9. 2023How Language Model Hallucinations Can Snowballcited by 310
  10. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  11. 2023Faithful Chain-of-Thought Reasoningcited by 285
  12. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  13. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 195
  14. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoningcited by 157
  15. 2022Minimizing the Accumulated Trajectory Error to Improve Dataset Distillationcited by 142
  16. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  17. 2019Causal Reasoning from Meta-reinforcement Learningcited by 53
  18. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Modelscited by 37
  19. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  20. 2018Generalize Symbolic Knowledge With Neural Rule Enginecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 14; 2026: 5.

24 papers.

Sort:

By area:

  1. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 123
  2. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 68
  3. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 62
  4. 2025Theoretical Benefit and Limitation of Diffusion Language Modelcited by 46
  5. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  6. 2024LiteSearch: Efficacious Tree Search for LLMcited by 30
  7. 2025Thinking Machines: A Survey of LLM based Reasoning Strategiescited by 25
  8. 2025Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMscited by 22
  9. 2024Revealing the Barriers of Language Agents in Planningcited by 20
  10. 2025Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfallscited by 13
  11. 2025A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematicscited by 11
  12. 2026Video Models Can Reason with Verifiable Rewardscited by 8
12 more
  1. 2025Reflection-Window Decoding: Text Generation with Selective Refinementcited by 7
  2. 2025Enhancing Large Language Model Reasoning with Reward Models: An Analytical Surveycited by 7
  3. 2025Unraveling Misinformation Propagation in LLM Reasoningcited by 6
  4. 2025Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalizationcited by 5
  5. 2026Learning Adaptive Reasoning Paths for Efficient Visual Reasoningcited by 5
  6. 2025Stepwise Informativeness Search for Efficient and Effective LLM Reasoningcited by 4
  7. 2025Towards Reasoning for PDE Foundation Models: A Reward-Model-Driven Inference-Time-Scaling Algorithmcited by 3
  8. 2024Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphscited by 2
  9. 2026Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoningcited by 1
  10. 2025CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Predictioncited by 0
  11. 2026Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Modelscited by 0
  12. 2026Provable Test-Time Scaling for Beam Search in LLM Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies
  2. 2025DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning
  3. 2024Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
  4. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains
  5. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  6. 2025Logical Reasoning with Outcome Reward Models for Test-Time Scaling
  7. 2025LLMSR@XLLM25: An Empirical Study of LLM for Structural Reasoning
  8. 2025Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning