paper-with-me

홈 › Papers

MASH: Modeling Abstention via Selective Help-Seeking

2025-10-01 · Mustafa Omer Gul, Claire Cardie, Tanya Goyal arxiv

LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In this paper, we introduce MASH (Modeling Abstention via Selective Help-seeking), a training framework that readily extracts abstentions from LLMs. Our key idea is that any external help-seeking by an LLM, i.e. search tool use, can serve as a proxy for abstention if the external help (search) is appropriately penalized while also rewarding answer accuracy. MASH operationalizes this idea using reinforcement learning with a pay-per-search reward. We run experiments on three knowledge-intensive QA datasets. Our results show that MASH substantially improves upon the selective help-seeking performance of prior efficient search approaches; on multi-hop datasets, it improves answer accuracy by 7.6%. Furthermore, MASH demonstrates strong off-the-shelf abstention performance, showcasing behavior competitive with prior abstention methods that additionally require predetermining model knowledge boundaries to construct training data. Overall, we show MASH training effectively aligns search tool use with parametric knowledge, which can be successfully leveraged for making abstention decisions and efficient search tool use

📄 PDF Abstract BibTeX arXiv:2510.01152

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Online Selective Classification with Limited Feedback

2021-10-27 · NeurIPS 2021 12 · Aditya Gangrade, Anil Kag, Ashok Cutkosky, Venkatesh Saligrama

Motivated by applications to resource-limited and safety-critical domains, we study selective classification in the online learning model, wherein a predictor may abstain from classifying an instance. For example, this m…

Classificationvalid

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

2026-04-20 · Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein 외 arxiv

LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods …

Mathematical ReasoningReinforcement Learning

CMasher: Scientific colormaps for making accessible, informative and 'cmashing' plots

2020-02-26

CMasher is a Python package that provides a curated collection of scientific colormaps, showcased in the online documentation (https://cmasher.readthedocs.io). The colormaps in CMasher are all designed to be perceptually…

Knowing When Not to Predict: Self Supervised Learning and Abstention for Safer DR Screening

2026-05-18 · Muskaan Chopra, Lorenz Sparrenberg, Jan H. Terheyden, Rafet Sifa arxiv

Self-supervised learning (SSL) is now a standard way to pretrain medical image models, but performance is still mostly judged by downstream accuracy. For safety-critical screening tasks such as diabetic retinopathy gradi…

Diabetic Retinopathy GradingSelf-Supervised Learning

Monster Mash: A Single-View Approach to Casual 3D Modeling and Animation

2020-12-01 · Marek Dvoroznak Daniel Sykora Brian Curless Cassidy Jonathan Curtis Olga Sorkine-Hornung David H. Salesin

Monster Mash is a new sketch-based modeling and animation tool that allows you to quickly sketch a character, inflate it into 3D, and promptly animate it. You can perform all interactions in the sketching plane. No 3D ma…

Image Generation