Newest papers

DIAL: Steerable Language Models with Distilled Instruction-Adherence Levels

Thanh Q. Tran, John Russell Himawan, Arun Verma, Kiwan Wong, Wei Xiao, Daniela Rus, Bryan Kian Hsiang Low · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31438 · open-access PDF

Arabic

عندما يقول المستخدم "الحفاظ على قصيرة"، ما هي قصيرة يجب أن تكون الاستجابة من LLM؟ بشكل عام، يستغرق المستخدمون والتطبيقات مستويات مختلفة من اتباع الإرشادات، ولكن الإرشادات لا توفر بالتأكيد السيطرة الكاملة علىها. لذلك، نحن ندرس "معدلات لغة قابلة للتحكم" التي توفر السيطرة الرقمية الكاملة على مدى ما تتبع النماذج الإرشادات العامة المحددة في النص. ومع ذلك، لا توفر الإرشادات الحالية معاً السيطرة الكاملة، والفعالية، والتوسع في جميع الإرشادات المختلفة.

Machine translation (Meta M2M100); the English original follows.

Abstract

When a user says "Keep it short", how short should the LLM's response be? More generally, users and applications require different levels of instruction adherence, but prompting does not reliably provide fine-grained control over them. We therefore study "steerable language models" that provide fine-grained numerical control over the degree to which models follow general instructions specified in text. However, existing approaches do not jointly offer fine-grained control, efficiency, and scalability across diverse instructions. To address this gap, we introduce DIAL (Distilled Instruction-Adh

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31438, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange