paper-with-me

Papers

AbductionRules: Training Transformers to Explain Unexpected Inputs

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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. This paper presents 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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense ReasoningLogical Reasoningscientific discovery

Similar Papers 제목 키워드 기반

AbductionRules: Training Transformers to Explain Unexpected Inputs

2022-03-23 · Findings (ACL) 2022 5 · Nathan Young, Qiming Bao, Joshua Bensemann, Michael Witbrock

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 unexpecte…

Common Sense ReasoningLogical Reasoningscientific discovery

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic

2026-01-30 · Xingyu Zhao, Darsh Sharma, Rheeya Uppaal, Yiqiao Zhong arxiv

Large language models (LLMs) often exhibit unexpected errors or unintended behavior, even at scale. While recent work reveals the discrepancy between LLMs and humans in skill compositions, the learning dynamics of skill …

Learning the greatest common divisor: explaining transformer predictions

2023-08-29 · François Charton

The predictions of small transformers, trained to calculate the greatest common divisor (GCD) of two positive integers, can be fully characterized by looking at model inputs and outputs. As training proceeds, the model l…

Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation

2026-02-10 · Donghwan Kim, Hyunsoo Yoon arxiv

Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We mitigate this likelihood paradox by man…

Semantic Similarity

Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4

2022-03-08 · William Berrios, Arturo Deza

Modern high-scoring models of vision in the brain score competition do not stem from Vision Transformers. However, in this paper, we provide evidence against the unexpected trend of Vision Transformers (ViT) being not pe…

Adversarial Robustness