activity
20222026
most citedGRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction

6 citations · 15 across the 22 of their papers we have counts for

collaborators

34 papers

cs.AI2026

Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

Jungseob Lee, Seongtae Hong, Dongyub Jude Lee +4

Speculative decoding accelerates generation without changing its output, yet on vision-language models (VLMs) it has been caught in a self-defeating cycle. The drafter stays autore…

cs.CL2026

The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice

Jungseob Lee, Jaehyung Seo, Heuiseok Lim

Hidden-state probes effectively detect LLM hallucinations, but the geometry of the signal remains poorly characterized, driving increasingly complex probe architectures. Across thr…

cs.CL2026

Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models

Jungseob Lee, Seungyoon Lee, Suhyune Son +4

A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer…

cs.CL2026

Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses

Sugyeong Eo, Heuiseok Lim

Although large language models (LLMs) have shown considerable progress in pragmatic language understanding, prior research has focused mainly on their comprehension of verbal behav…

cs.CL2026

No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand

Jimin Jung, MyoungJin Kim, Jaehyung Seo +1

The Plain Writing Act in the United States requires government documents to be accessible in clear and simple language that the general public can easily understand, yet existing s…

cs.AI2026

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering

Joongmin Shin, Gyuho Shim, Jeongbae Park +2

Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in l…