activity
20242026
most citedMitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding

1 citations · 2 across the 18 of their papers we have counts for

collaborators
Showing 2026Show all

6 papers · 1 filter

cs.LG2026

Carryover Drafting: Recycling Rejected States for Speculative Decoding

Jahyun Koo, Sunghyeon Woo, Jaeeun Kil +4

Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, ve…

cs.AI2026

PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations

Hyojeong Yu, Hyukhun Koh, Minsung Kim +2

Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on f…

cs.CL2026

Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs

Jiwon Moon, Yerin Hwang, Kyomin Jung

Instruction hierarchy (IH) requires models to prioritize instructions by source, ensuring that higher-priority instructions override lower-priority ones. Despite its importance for…

cs.CL2026

Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset

Hyojeong Yu, Hyukhun Koh, Minsung Kim +1

Formality transfer is commonly framed as a symmetric bidirectional task between informal and formal registers. We argue that this framing conceals a supervision design flaw in exis…

cs.CL2026

When Wording Steers the Evaluation: Framing Bias in LLM judges

Yerin Hwang, Dongryeol Lee, Taegwan Kang +2

Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the…

cs.CL2026

Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation

Dongryeol Lee, Yerin Hwang, Taegwan Kang +3

While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about the…