Pith. sign in

REVIEW 13 cited by

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.12295 v2 pith:HFZ74HDA submitted 2023-05-20 cs.CL cs.AI

classification cs.CLcs.AI
keywords symboliclogic-lmlogicalllmsreasoninglanguagefaithfullarge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which integrates LLMs with symbolic solvers to improve logical problem-solving. Our method first utilizes LLMs to translate a natural language problem into a symbolic formulation. Afterward, a deterministic symbolic solver performs inference on the formulated problem. We also introduce a self-refinement module, which utilizes the symbolic solver's error messages to revise symbolic formalizations. We demonstrate Logic-LM's effectiveness on five logical reasoning datasets: ProofWriter, PrOntoQA, FOLIO, LogicalDeduction, and AR-LSAT. On average, Logic-LM achieves a significant performance boost of 39.2% over using LLM alone with standard prompting and 18.4% over LLM with chain-of-thought prompting. Our findings suggest that Logic-LM, by combining LLMs with symbolic logic, offers a promising avenue for faithful logical reasoning. Code and data are publicly available at https://github.com/teacherpeterpan/Logic-LLM.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?

    cs.CL 2026-07 conditional novelty 6.5 of 10

    CreditCardQA shows LLMs err mainly on credit-card contractual conditions and comparisons, not arithmetic, with Program-of-Thought narrowing open–closed model gaps.

  2. Training Large Language Models for Self-Explanation Faithfulness

    cs.LG 2026-07 conditional novelty 6.0 of 10

    RL fine-tuning with a counterfactual mention/influence reward raises LLM self-explanation faithfulness (Phi-CCT) from near zero to ~0.66 in-distribution for two 8B models, with partial transfer to held-out tasks.

  3. Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Learned soft prefixes reliably flip correct syllogistic judgments in LLMs, transferring across unseen forms and interfaces and behaving mainly as a broad answer preference rather than a transferable logical operation.

  4. Throttling Web Agents Using Reasoning Gates

    cs.AI 2025-09 conditional novelty 6.0 of 10

    Rebus-based reasoning gates, puzzles built from random word/domain clue sets, impose token costs on LM web agents that are up to 9.2x the generator's cost.

  5. Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation

    cs.IR 2025-09 reject novelty 6.0 of 10

    SolveRank trains a contrastive retriever on LLM-generated logically equivalent problem variants and reports improved retrieval and code generation, though the retrieval evaluation is circular.

  6. Confidently Wrong: Exception Chain Collapse in Frontier LLM Rule Evaluation

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Nested exception-chain eligibility breaks frontier LLMs in unstable ways; an SMT execution layer makes outcomes deterministic given authored rules.

  7. R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems

    cs.IR 2025-07 conditional novelty 5.0 of 10

    R4ec trains a small reflection model to critique and refine LLM-generated user and item knowledge, which then improves downstream recommendation accuracy.

  8. Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding

    cs.CL 2025-07 conditional novelty 5.0 of 10

    DeepSeek-R1-distilled models show higher multi-document QA accuracy than their base counterparts and flatter position-bias curves, especially with 50-80 documents.

  9. DipSVD: Dual-importance Protected SVD for Efficient LLM Compression

    cs.LG 2025-06 reject novelty 5.0 of 10

    DipSVD combines channel-weighted whitening with layer-wise compression ratios and reports better perplexity and accuracy than existing SVD-based LLM compression methods.

  10. From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs

    cs.AI 2025-09 conditional novelty 4.0 of 10

    A guideline-and-refinement prompting framework distills reasoning rules from past successes and failures, applies them stepwise with per-step correction, and reports gains over CoT, ReAct, ToT, Beats, and FoT on selec...

  11. From Legal Text to Tech Specs: Generative AI's Interpretation of Consent in Privacy Law

    cs.SE 2025-07 conditional novelty 4.0 of 10

    An LLM pipeline that flags and fixes non-compliant consent use cases works imperfectly: it catches about two-thirds of relevant cases with reasoning prompts, and most of its fixes are legally sound but logically inconsistent.

  12. Integrating External Tools with Large Language Models to Improve Accuracy

    cs.CL 2025-07 reject novelty 2.0 of 10

    A tool-augmented LLM framework, Athena, reports 83% math and 88% science accuracy on small MMLU subsets, beating GPT-4o, LLaMA-Large, Mistral-Large, Phi-Large, and GPT-3.5.

  13. From Provable Correctness to Probabilistic Generation: A Comparative Review of Program Synthesis Paradigms

    cs.PL 2025-07 conditional

    A bachelor's thesis surveys deductive, inductive, sketch-based, LLM-based, and neuro-symbolic program synthesis, emphasizing correctness versus usability trade-offs.

Pith tools