# AbductionRules: Training Transformers to Explain Unexpected Inputs

arXiv: https://arxiv.org/abs/2203.12186 · HTML: https://mlsanity.com/paper/2203.12186/

## Key facts

- Cited by 17 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Generative Language Modeling for Automated Theorem Proving](https://mlsanity.com/paper/2009.03393/) (2020)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [Abduction-Based Explanations for Machine Learning Models](https://mlsanity.com/paper/1811.10656/) (2018)
- [On the Computational Power of Transformers and its Implications in Sequence Modeling](https://mlsanity.com/paper/2006.09286/) (2020)
- [NaturalProofs: Mathematical Theorem Proving in Natural Language](https://mlsanity.com/paper/2104.01112/) (2021)
- [PRover: Proof Generation for Interpretable Reasoning over Rules](https://mlsanity.com/paper/2010.02830/) (2020)
- [Measuring Systematic Generalization in Neural Proof Generation with Transformers](https://mlsanity.com/paper/2009.14786/) (2020)
- [The Chess Transformer: Mastering Play using Generative Language Models](https://mlsanity.com/paper/2008.04057/) (2020)
- [multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning](https://mlsanity.com/paper/2106.01354/) (2021)

## Built on by (most cited first, 17 of 17)

- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [Large Language Models Are Not Strong Abstract Reasoners](https://mlsanity.com/paper/2305.19555/) (2023)
- [A Survey of Useful LLM Evaluation](https://mlsanity.com/paper/2406.00936/) (2024)
- [Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus](https://mlsanity.com/paper/2411.12498/) (2024)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models](https://mlsanity.com/paper/2505.15801/) (2025)
- [Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation](https://mlsanity.com/paper/2207.14000/) (2022)
- [Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning](https://mlsanity.com/paper/2310.09430/) (2023)
- [IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs](https://mlsanity.com/paper/2409.05559/) (2024)
- [Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors](https://mlsanity.com/paper/2512.06393/) (2025)
- [Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs](https://mlsanity.com/paper/2604.08016/) (2026)
- [Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction](https://mlsanity.com/paper/2310.04671/) (2023)
- [Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text](https://mlsanity.com/paper/2301.02983/) (2023)
- [LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models](https://mlsanity.com/paper/2510.11031/) (2025)
- [SciR: A Controllable Benchmark for Scientific Reasoning in LLMs](https://mlsanity.com/paper/2606.13020/) (2026)

## 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.