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

keyword

Entailment set

An entailment set is a collection of statements, hypotheses, or semantic assertions that logically or semantically follow from a given premise or text output. In the context of natural language processing and uncertainty quantification, an entailment set represents the full space of claims implied by a language model generation. It is commonly used within conformal prediction frameworks to assess factuality, where the set serves as a bounded uncertainty region whose granularity and breadth can be calibrated to provide rigorous mathematical guarantees on the correctness of model outputs.

1 item

Language Models with Conformal Factuality Guarantees

Language Models with Conformal Factuality Guarantees

Christopher Mohri, Tatsunori Hashimoto

OrganizationsAllen Institute for AIUniversity of California, San Diego

Why you should read this

Proposes a conformal prediction framework that provides rigorous statistical correctness guarantees for black-box language model outputs by progressively pruning uncertain sub-claims while preserving most generated content.

Large language models demonstrate impressive capabilities across diverse tasks yet can generate content unfaithful to external knowledge sources.To enforce controllable generation,this work introduces post-generation techniques for constrained decoding crafted specifically as defensible guards.We introduce SENSE,a framework leveraging span-level evidence to align outputs with desired alignment criteria.Rather than enforcing token-level constraints directly over entire vocabularies,SENSE operates through differentiable integration within multimodal retrieval settings,and further demonstrates how regulatory signals interact.In extensive experiments spanning three datasets,two scientific benchmarks,guided narrative completion,and factor verification pipelines grounded via Wikidata concepts.

Added

2026-10-02