mlsanityData to 14 Oct 2026

ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language

arXiv 2012.13048 ↗First posted 24 Dec 2020cs.CL cs.AIcited by 324

Not on the map. Why?

Cited by 204 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory has not yet been demonstrated, and methods for reconstructing proofs of answers are imperfect. In this work we show that a generative model, called ProofWriter, can reliably generate both implications of a theory and the natural language proof(s) that support them. In particular, iterating a 1-step implication generator results in proofs that are highly reliable, and represent actual model decisions (rather than post-hoc rationalizations). On the RuleTaker dataset, the accuracy of ProofWriter's proofs exceed previous methods by +9% absolute, and in a way that generalizes to proof depths unseen in training and on out-of-domain problems. We also show that generative techniques can perform a type of abduction with high precision: Given a theory and an unprovable conclusion, identify a missing fact that allows the conclusion to be proved, along with a proof. These results significantly improve the viability of neural methods for systematically reasoning over natural language.

Key facts. Cited by 324 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 46; 2023: 49; 2024: 49; 2025: 75; 2026: 94.

324 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,576
  2. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  3. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  4. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  5. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 503
  6. 2023Cognitive Architectures for Language Agentscited by 429
  7. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  8. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 337
  9. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  10. 2022Reasoning with Language Model Prompting: A Surveycited by 252
  11. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  12. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 236
38 more
  1. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 235
  2. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 215
  3. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 177
  4. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  5. 2022A Review on Language Models as Knowledge Basescited by 157
  6. 2021Explaining Answers with Entailment Treescited by 152
  7. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 143
  8. 2022UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expressioncited by 137
  9. 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoningcited by 136
  10. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  11. 2022Faithful Reasoning Using Large Language Modelscited by 130
  12. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  13. 2025BIG-Bench Extra Hardcited by 125
  14. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 124
  15. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 123
  16. 2023GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoningcited by 108
  17. 2023SatLM: Satisfiability-Aided Language Models Using Declarative Promptingcited by 102
  18. 2024Faithful Logical Reasoning via Symbolic Chain-of-Thoughtcited by 100
  19. 2023Shepherd: A Critic for Language Model Generationcited by 97
  20. 2023Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Trackercited by 95
  21. 2023Cumulative Reasoning with Large Language Modelscited by 94
  22. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilitiescited by 89
  23. 2024Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoningcited by 88
  24. 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examplescited by 84
  25. 2021NaturalProofs: Mathematical Theorem Proving in Natural Languagecited by 81
  26. 2023Exposing Attention Glitches with Flip-Flop Language Modelingcited by 75
  27. 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
  28. 2024LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Modelscited by 68
  29. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  30. 2024A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languagescited by 66
  31. 2023Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyondcited by 65
  32. 2023Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasonerscited by 63
  33. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  34. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 63
  35. 2023Natural Language Reasoning, A Surveycited by 61
  36. 2024A Survey on Deep Learning for Theorem Provingcited by 57
  37. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  38. 2025Empowering LLMs with Logical Reasoning: A Comprehensive Surveycited by 51

50 most cited of 324 All 324 (JSON)