AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
[Submitted on 17 Sep 2026] Title:Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention View a PDF of the paper titled Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention, by Jongbin Won and 2 other authors View PDF HTML (experimental) Abstract:Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to handle heterogeneous retrieval failures in a single step, resulting in limited abstention performance and high computational costs. We instead decompose retrieval failures into two distinct states: (i) the unanswerable state, where the required evidence is absent, and (ii) the distracted state, where relevant evidence is mixed with conflicting, negated, or adversarial information. Based on this decomposition, we introduce a lightweight module (Sieve) that screens retrieved document sets for distracting evidence before invoking a costly LLM (Sage) for grounded generation and abstention. Evaluated across both general and high-stakes expert domains, our Sieve and Sage framework preemptively detects distracting noise, improving system accuracy by up to 69.4 percentage points and Macro-F1 by 55.2 percentage points compared to one-stage baselines. Furthermore, it achieves up to a 1.99x speedup, establishing a highly efficient and reliable abstention pipeline for RALM with abstention. Comments: 20 pages, 6 figures, accepted at EMNLP 2026 Findings Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2609.35794 [cs.CL] (or arXiv:2609.35794v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2609.35794 arXiv-issued DOI via DataCite (pending registration) Submission history From: Jongbin Won [view email] [v1] Thu, 17 Sep 2026 04:59:56 UTC (6,882 KB) Full-text links: Access Paper: View a PDF of the paper titled Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention, by Jongbin Won and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-09 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)