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
사용자가 "그것을 짧게 유지하십시오"라고 말할 때, LLM의 응답은 얼마나 짧아야합니까? 더 일반적으로 사용자와 응용 프로그램은 지침 준수의 다른 수준을 필요로하지만, 촉구는 신뢰할 수있게 그들에 대한 미묘한 제어를 제공하지 않습니다. 따라서 우리는 모델이 텍스트에 지정된 일반 지침을 따르는 정도에 대해 미묘한 숫자 제어를 제공하는 "통제 가능한 언어 모델"을 연구합니다.
Machine translation (Meta M2M100); the English original follows.
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
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange