mlsanityData to 7 Oct 2026

AbductionRules: Training Transformers to Explain Unexpected Inputs

arXiv 2203.12186 ↗First posted 23 Mar 2022cs.CLcited by 17

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has been underexplored despite significant applications to scientific discovery, common-sense reasoning, and model interpretability. We present AbductionRules, a group of natural language datasets designed to train and test generalisable abduction over natural-language knowledge bases. We use these datasets to finetune pretrained Transformers and discuss their performance, finding that our models learned generalisable abductive techniques but also learned to exploit the structure of our data. Finally, we discuss the viability of this approach to abductive reasoning and ways in which it may be improved in future work.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 15 of its 23 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

15 of 23 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2018Image Transformercited by 770
  5. 2020Generative Language Modeling for Automated Theorem Provingcited by 379
  6. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 309
  7. 2019Abductive Commonsense Reasoningcited by 300
  8. 2020Transformers as Soft Reasoners over Languagecited by 265
  9. 2018Abduction-Based Explanations for Machine Learning Modelscited by 159
  10. 2020On the Computational Power of Transformers and its Implications in Sequence Modelingcited by 85
  11. 2021NaturalProofs: Mathematical Theorem Proving in Natural Languagecited by 80
  12. 2020PRover: Proof Generation for Interpretable Reasoning over Rulescited by 53
3 more
  1. 2020Measuring Systematic Generalization in Neural Proof Generation with Transformerscited by 43
  2. 2020The Chess Transformer: Mastering Play using Generative Language Modelscited by 36
  3. 2021multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoningcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 3; 2025: 4; 2026: 2.

17 papers.

Sort:

By area:

  1. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  2. 2023Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyondcited by 65
  3. 2023Natural Language Reasoning, A Surveycited by 61
  4. 2023Large Language Models Are Not Strong Abstract Reasonerscited by 52
  5. 2024Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpuscited by 29
  6. 2024A Survey of Useful LLM Evaluationcited by 28
  7. 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 26
  8. 2025VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Modelscited by 19
  9. 2022Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisationcited by 15
  10. 2023Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoningcited by 10
  11. 2024IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMscited by 9
  12. 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMscited by 5
5 more
  1. 2023Exploring the Potential of Multi-Modal AI for Driving Hazard Predictioncited by 4
  2. 2025Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priorscited by 4
  3. 2023Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Textcited by 2
  4. 2025LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Modelscited by 2
  5. 2026SciR: A Controllable Benchmark for Scientific Reasoning in LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GEAR: A General Evaluation Framework for Abductive Reasoning
  2. 2023Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations
  3. 2023UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations
  4. 2023Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
  5. 2026Graph of States: Solving Abductive Tasks with Large Language Models
  6. 2026Abductive Reasoning with Syllogistic Forms in Large Language Models
  7. 2026Abductive Reasoning with Probabilistic Commonsense
  8. 2026LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos