Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

multi-premise entailments

Multi-premise entailments refer to logical or textual inference relationships where a hypothesis or conclusion is derived from a combination of two or more distinct premise statements acting together rather than from a single standalone premise. In natural language processing and computational reasoning, determining a multi-premise entailment requires aggregating complementary information across multiple facts to evaluate whether the collective evidence fully justifies the target claim. This extends standard single-premise natural language inference by supporting multi-step deductions and structured reasoning chains, which are essential for tasks like multi-hop question answering, fact verification, and faithful explanation generation where no individual piece of evidence is sufficient on its own to substantiate the conclusion.

1 item

Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning

Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning

Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark

OrganizationsAllen Institute for AI

Why you should read this

Proposes a question-answering framework that couples backward-chaining entailment generation with self-query verification to construct multi-step reasoning trees directly reflecting a language model's internal beliefs.

Our goal is for a system to be able to answer questions and justify its answers with a faithful and truthful chain of reasoning. We present Entailer, a system that produces chains of reasoning by decomposing the question into subquestions and then answering each subquestion using a textual entailment model. The model is trained on a new dataset of 10K examples of multistep reasoning, and uses a novel method to generate the training data automatically from a large corpus. Entailer achieves state-of-the-art results on two multistep reasoning datasets, and its reasoning chains are more faithful and truthful than those of a large language model, as measured by human evaluation and a new automatic metric. We also show that Entailer can be used to improve the performance of a large language model by providing it with a faithful derivation of the answer.

Added

2026-10-03