# Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs

arXiv: https://arxiv.org/abs/2604.08016 · HTML: https://mlsanity.com/paper/2604.08016/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 72 of its 108 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

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

## Builds on (most cited first, 30 of 72)

- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning](https://mlsanity.com/paper/2310.16049/) (2023)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play](https://mlsanity.com/paper/2405.06373/) (2024)
- [Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning](https://mlsanity.com/paper/2010.05906/) (2020)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Steering Large Language Model Activations in Sparse Spaces](https://mlsanity.com/paper/2503.00177/) (2025)
- [e-CARE: a New Dataset for Exploring Explainable Causal Reasoning](https://mlsanity.com/paper/2205.05849/) (2022)
- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning](https://mlsanity.com/paper/2202.04800/) (2022)
- [Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.00836/) (2023)
- [Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation](https://mlsanity.com/paper/2407.08940/) (2024)
- [Visual Abductive Reasoning](https://mlsanity.com/paper/2203.14040/) (2022)
- [Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study](https://mlsanity.com/paper/2308.14321/) (2023)
- [Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning](https://mlsanity.com/paper/2402.06025/) (2024)

## Built on by (most cited first, 5 of 5)

- [LLMs Don't Pay for the Jump](https://mlsanity.com/paper/2608.14397/) (2026)
- [LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos](https://mlsanity.com/paper/2607.12733/) (2026)
- [CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs](https://mlsanity.com/paper/2608.14791/) (2026)
- [When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models](https://mlsanity.com/paper/2608.26187/) (2026)
- [Thinking effort aligns between humans and reasoning models in abductive reasoning](https://mlsanity.com/paper/2609.01867/) (2026)

## Abstract (arXiv)

Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an observation--has been relatively underexplored in Large Language Models (LLMs). Despite the rapid advancement of LLMs, the exploration of abductive reasoning and its diverse facets has thus far been disjointed rather than cohesive. This paper presents the first survey of abductive reasoning in LLMs, tracing its trajectory from philosophical foundations to contemporary AI implementations. To address the widespread conceptual confusion and disjointed task definitions prevalent in the field, we establish a unified two-stage definition that formally categorizes prior work. This definition disentangles abduction into Hypothesis Generation, where models bridge epistemic gaps to produce candidate explanations, and Hypothesis Selection, where the generated candidates are evaluated and the most plausible explanation is chosen. Building upon this foundation, we present a comprehensive taxonomy of the literature, categorizing prior work based on their abductive tasks, datasets, underlying methodologies, and evaluation strategies. In order to ground our framework empirically, we conduct a compact benchmark study of current LLMs on abductive tasks, together with targeted comparative analyses across model sizes, model families, evaluation styles, and the distinct generation-versus-selection task typologies. Moreover, by synthesizing recent empirical results, we examine how LLM performance on abductive reasoning relates to deductive and inductive tasks, providing insights into their broader reasoning capabilities. Our analysis reveals critical gaps in current approaches--from static benchmark design and narrow domain coverage to narrow training frameworks and limited mechanistic understanding of abductive processes...