# L2R2: Leveraging Ranking for Abductive Reasoning

arXiv: https://arxiv.org/abs/2005.11223 · HTML: https://mlsanity.com/paper/2005.11223/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2020.

## Built on by (most cited first, 8 of 8)

- [UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark](https://mlsanity.com/paper/2103.13009/) (2021)
- [ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification](https://mlsanity.com/paper/2203.02225/) (2022)
- [Self-Consistent Narrative Prompts on Abductive Natural Language Inference](https://mlsanity.com/paper/2309.08303/) (2023)
- [Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference](https://mlsanity.com/paper/2202.10408/) (2022)
- [Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs](https://mlsanity.com/paper/2604.08016/) (2026)
- [Generating Hypothetical Events for Abductive Inference](https://mlsanity.com/paper/2106.03973/) (2021)
- [Interactive Model with Structural Loss for Language-based Abductive Reasoning](https://mlsanity.com/paper/2112.00284/) (2021)
- [Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding](https://mlsanity.com/paper/2301.03765/) (2023)

## Abstract (arXiv)

The abductive natural language inference task (αNLI) is proposed to evaluate the abductive reasoning ability of a learning system. In the αNLI task, two observations are given and the most plausible hypothesis is asked to pick out from the candidates. Existing methods simply formulate it as a classification problem, thus a cross-entropy log-loss objective is used during training. However, discriminating true from false does not measure the plausibility of a hypothesis, for all the hypotheses have a chance to happen, only the probabilities are different. To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities. With this new perspective, a novel L2R2 approach is proposed under the learning-to-rank framework. Firstly, training samples are reorganized into a ranking form, where two observations and their hypotheses are treated as the query and a set of candidate documents respectively. Then, an ESIM model or pre-trained language model, e.g. BERT or RoBERTa, is obtained as the scoring function. Finally, the loss functions for the ranking task can be either pair-wise or list-wise for training. The experimental results on the ART dataset reach the state-of-the-art in the public leaderboard.