Large language models (LLMs) have achieved significant advancements in natural language processing tasks, but they remain prone to generating hallucinations—outputs that are logically inconsistent or factually incorrect. While previous research has primarily focused on hallucinations in affirmative contexts, how negate...
Jaehyung Seo, Hyeonseok Moon, Heu-Jeoung Lim· ACM Transactions on Knowledg...· 0 citations
Agentic tasks require a large language model to interact with the world, navigating information and gathering evidence across multiple steps with restricted resources. Due to this complexity, agentic task failures arise from various sources, and pinpointing these failure causes is essential to diagnose and improve agen...
Chanhee Park, Jeongho Yoon, Sun Han et al.· 0 citations
Cloud-based large language models (LLMs) require users to disclose plaintext data to service providers, creating privacy risks in sensitive domains. Existing privacy-preserving approaches often trade utility for protection, incur substantial computational or communication overhead, remain vulnerable to reconstruction f...
Jeongho Yoon, Chanhee Park, Yong-Chan Chun et al.· 0 citations
DART is introduced, a training-free routing framework that samples two cheap no-think drafts, accepts direct answering when the drafts agree, and predicts a thinking budget from draft entropy when they disagree, and preserves or improves always-thinking accuracy in most settings while reducing thinking-token use.
Jungseob Lee, Seongtae Hong, Seungjun Lee et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
