mlsanityData to 7 Oct 2026

Faithful Logical Reasoning via Symbolic Chain-of-Thought

arXiv 2405.18357 ↗First posted 28 May 2024cs.CLcited by 99

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

While the recent Chain-of-Thought (CoT) technique enhances the reasoning ability of large language models (LLMs) with the theory of mind, it might still struggle in handling logical reasoning that relies much on symbolic expressions and rigid deducing rules. To strengthen the logical reasoning capability of LLMs, we propose a novel Symbolic Chain-of-Thought, namely SymbCoT, a fully LLM-based framework that integrates symbolic expressions and logic rules with CoT prompting. Technically, building upon an LLM, SymbCoT 1) first translates the natural language context into the symbolic format, and then 2) derives a step-by-step plan to solve the problem with symbolic logical rules, 3) followed by a verifier to check the translation and reasoning chain. Via thorough evaluations on 5 standard datasets with both First-Order Logic and Constraint Optimization symbolic expressions, SymbCoT shows striking improvements over the CoT method consistently, meanwhile refreshing the current state-of-the-art performances. We further demonstrate that our system advances in more faithful, flexible, and explainable logical reasoning. To our knowledge, this is the first to combine symbolic expressions and rules into CoT for logical reasoning with LLMs. Code is open at https://github.com/Aiden0526/SymbCoT.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 30 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

17 of 30 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting26 May
  2. 2023Reasoning Implicit Sentiment with Chain-of-Thought Prompting18 May
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 14

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  3. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 610
  4. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  5. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  6. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  7. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
  8. 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognitioncited by 151
  9. 2023Structured Chain-of-Thought Prompting for Code Generationcited by 136
  10. 2022Bidirectional Language Models Are Also Few-shot Learnerscited by 48
  11. 2022Formal Specifications from Natural Languagecited by 33
  12. 2024Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Taskscited by 22
2 more
  1. 2023Reasoning in Large Language Models Through Symbolic Math Word Problemscited by 16
  2. 2023Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thoughtcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 15; 2025: 57; 2026: 27.

99 papers.

Sort:

By area:

  1. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  2. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  3. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  4. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51
  5. 2025CoT Red-Handed: Stress Testing Chain-of-Thought Monitoringcited by 49
  6. 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lenscited by 42
  7. 2025Unveiling the Key Factors for Distilling Chain-of-Thought Reasoningcited by 40
  8. 2025Semantic-Aware Logical Reasoning via a Semiotic Frameworkcited by 32
  9. 2024CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Modelscited by 29
  10. 2024Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoningcited by 27
  11. 2026Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoningcited by 24
  12. 2025Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendationcited by 21
38 more
  1. 2025Learning to Reason via Mixture-of-Thought for Logical Reasoningcited by 20
  2. 2025How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencodingcited by 19
  3. 2024Symbolic Working Memory Enhances Language Models for Complex Rule Applicationcited by 17
  4. 2025Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractionscited by 17
  5. 2025Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Studycited by 17
  6. 2025Think Clearly: Improving Reasoning via Redundant Token Pruningcited by 17
  7. 2024Can Transformers Reason Logically? A Study in SAT Solvingcited by 16
  8. 2024CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoningcited by 16
  9. 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domainscited by 15
  10. 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compressioncited by 15
  11. 2025Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoningcited by 14
  12. 2025Theorem Prover as a Judge for Synthetic Data Generationcited by 13
  13. 2025Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAGcited by 13
  14. 2025VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoningcited by 12
  15. 2024HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoningcited by 11
  16. 2025Blueprint First, Model Second: A Framework for Deterministic LLM Workflowcited by 11
  17. 2024Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Informationcited by 10
  18. 2024Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoningcited by 10
  19. 2025DecisionFlow: Advancing Large Language Model as Principled Decision Makercited by 10
  20. 2025Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planningcited by 10
  21. 2025VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checkscited by 10
  22. 2025A Neurosymbolic Approach to Natural Language Formalization and Verificationcited by 8
  23. 2024FLARE: Faithful Logic-Aided Reasoning and Explorationcited by 7
  24. 2025HoarePrompt: Structural Reasoning About Program Correctness in Natural Languagecited by 7
  25. 2025MuSLR: Multimodal Symbolic Logical Reasoningcited by 7
  26. 2025SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokenscited by 7
  27. 2025Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systemscited by 6
  28. 2025RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Samplingcited by 6
  29. 2025LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervisioncited by 6
  30. 2025AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Modelscited by 5
  31. 2025Reason from Future: Reverse Thought Chain Enhances LLM Reasoningcited by 5
  32. 2024Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedbackcited by 4
  33. 2024Boosting Deductive Reasoning with Step Signals In RLHFcited by 4
  34. 2025Thinking Machines: Mathematical Reasoning in the Age of LLMscited by 4
  35. 2025Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoningcited by 4
  36. 2025R-Debater: Retrieval-Augmented Debate Generation through Argumentative Memorycited by 4
  37. 2026OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inferencecited by 4
  38. 2025Integrating Expert Knowledge into Logical Programs via LLMscited by 3

50 most cited of 99 All 99 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Faithful Chain-of-Thought Reasoning
  2. 2022Evaluating Step-by-Step Reasoning through Symbolic Verification
  3. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  4. 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
  5. 2026Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency
  6. 2025Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
  7. 2024On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
  8. 2024A Closer Look at Logical Reasoning with LLMs: The Choice of Tool Matters