DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge
Paper recorded by Signals 4 on 2026-10-20 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-20 on arXiv · recorded by Signals 4 on 2026-10-21
Category: cs.CL · 自然语言处理 · first seen 2026-10-21
Abstract
Reliable retrieval-augmented generation (RAG) requires recognizing when neither retrieved documents nor parametric knowledge supports an answer. We introduce DeclineCraft, a dynamic abstention benchmark whose unanswerable questions target Minecraft feature additions after a corpus cut-off, with audits of possible parametric exposure. Later cut-offs support evaluation of future models. Across 27 LL
Read on arXiv →
Cite this page: DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge: the #207 most recent of 660 cs.CL papers we have recorded (as of 2026-10-20). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/declinecraft-a-rag-abstention-benchmark-for-jointly-measuring-combined-retrieval.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free