3 citations · 6 across the 26 of their papers we have counts for
13 papers · 1 filter
ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models
Myunghoon Kang, Jungseob Lee, Jaehyung Seo +1
Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they often fail to recover once the…
Predicting and Repairing Merge Collapse in Large Language Models
Jungseob Lee, Seungyoon Lee, Sugyeong Eo +3
Large language models fine-tuned from a shared base can be merged by averaging their task vectors, but some merges collapse far below the base model, and common merge operators giv…
Distilling Directional Verification
Jungseob Lee, Sugyeong Eo, Seongtae Hong +4
Knowledge distillation aims to transfer the factual knowledge of large language models to smaller models for efficient deployment. Yet a teacher may recall a relation in one direct…
PILAR: A Page-Grounded Unified Evidence Representation via an Entity-Linked Assertion Graph for Open-Domain QA Agents over Multimodal Document Corpora
Joongmin Shin, Gyuho Shim, Jung-hun Lee +1
Open-domain question answering (ODQA) over multimodal document corpora requires linking evidence scattered across text, tables, and figures. Existing systems often store these sour…
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, but on vision-language models (VLMs) a self-reinforcing cycle holds it back. Because an autoregressive draf…
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…
CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan +30
Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking pract…
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5
Refusal on a safety benchmark does not reveal how stable that behavior will remain after model updates. Benign downstream fine-tuning can weaken refusal, yet behavioral evaluations…
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
Jungseob Lee, Seongtae Hong, Seungjun Lee +7
Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for each query, so easy problems avoid…
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…
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…
M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
Joongmin Shin, Jeongbae Park, Jaehyung Seo +1
In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centr…
MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
Joongmin Shin, Chanjun Park, Jeongbae Park +2
RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial doc…