Cost-equalised comparison of answer-or-defer signals for retrieval-augmented generation: measurements and analysis
Abstract
Derived measurements, analysis code and the sealed pre-registration for a comparison of ten answer-or-defer signals in retrieval-augmented generation, evaluated at equal coverage and at equal cost over 2,748 human-annotated responses from four open generators, under three constructions of the acceptability label and three task regimes. Contains per-response signal scores indexed by RAGTruth identifier, every reported result in machine-readable form, and the full analysis pipeline with self-tests. No source texts are redistributed.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.