# UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations

arXiv: https://arxiv.org/abs/2311.08469 · HTML: https://mlsanity.com/paper/2311.08469/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 4 of its 33 references that are in the map.
- First posted on arXiv 14 Nov 2023.

## Placed in

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

## Builds on (most cited first, 4 of 4)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing](https://mlsanity.com/paper/2305.16635/) (2023)

## Built on by (most cited first, 19 of 19)

- [Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus](https://mlsanity.com/paper/2411.12498/) (2024)
- [Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas](https://mlsanity.com/paper/2501.11549/) (2025)
- [LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning](https://mlsanity.com/paper/2502.11176/) (2025)
- [Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs](https://mlsanity.com/paper/2505.20948/) (2025)
- [The Future of Open Human Feedback](https://mlsanity.com/paper/2408.16961/) (2024)
- [Epistemology of Language Models: Do Language Models Have Holistic Knowledge?](https://mlsanity.com/paper/2403.12862/) (2024)
- [Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model](https://mlsanity.com/paper/2510.11462/) (2025)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Enhancing Transformers for Generalizable First-Order Logical Entailment](https://mlsanity.com/paper/2501.00759/) (2025)
- [Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs](https://mlsanity.com/paper/2604.08016/) (2026)
- [DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence?](https://mlsanity.com/paper/2406.12641/) (2024)
- [Towards Quantifying Commonsense Reasoning with Mechanistic Insights](https://mlsanity.com/paper/2504.10077/) (2025)
- [Societal Impacts Research Requires Benchmarks for Creative Composition Tasks](https://mlsanity.com/paper/2504.06549/) (2025)
- [Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data](https://mlsanity.com/paper/2508.00741/) (2025)
- [VIVA+: Human-Centered Situational Decision-Making](https://mlsanity.com/paper/2509.23698/) (2025)
- [Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd](https://mlsanity.com/paper/2602.01561/) (2026)
- [Explanation Generation for Contradiction Reconciliation with LLMs](https://mlsanity.com/paper/2603.22735/) (2026)
- [HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge Graphs](https://mlsanity.com/paper/2605.31370/) (2026)
- [Evaluating Whether LLMs Can Reliably Connect the DOTs?](https://mlsanity.com/paper/2609.38406/) (2026)

## Abstract (arXiv)

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the ability to model unusual, unexpected, and unlikely situations, we explore the task of uncommonsense abductive reasoning. Given a piece of context with an unexpected outcome, this task requires reasoning abductively to generate an explanation that makes the unexpected outcome more likely in the context. To this end, we curate and release a new English language corpus called UNcommonsense. We characterize the performance differences between human explainers and the best-performing large language models, finding that model-enhanced human-written explanations achieve the highest quality by trading off between specificity and diversity. Finally, we experiment with several imitation learning algorithms to train open and accessible language models on this task. When compared with the vanilla supervised fine-tuning approach, these methods consistently reduce lose rates on both common and uncommonsense abductive reasoning judged by human evaluators.