6 citations · 23 across the 46 of their papers we have counts for
53 papers
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…
Generalizable Lifelong Model Editing via Preference Optimization
Dahyun Jung, Suhyune Son, Heuiseok Lim
Knowledge editing enables rapid updates of specific factual knowledge in large language models (LLMs) without full retraining. However, more realistic scenarios call for a lifelong…
Faster Block-Diffusion Serving with Distribution-Free Risk Guarantees
Jungseob Lee, Dongyub Jude Lee, Chanjun Park +2
Block-diffusion language models are served at hand-picked operating points, such as acceptance thresholds, buffer depth, schedule, checkpoint and precision, and each point is chose…
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…
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…
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…
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…
Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
Gyuho Shim, Seongtae Hong, Heuiseok Lim
Recent advances in Large Language Models (LLMs) have significantly improved the field of Document AI, demonstrating remarkable performance on document understanding tasks such as q…
LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
Dongjun Kim, Jeongho Yoon, Chanjun Park +1
Dense retrieval in multilingual settings often searches over mixed-language collections, yet multilingual embeddings encode language identity alongside semantics. This language sig…
The Impact of Negated Text on Hallucination with Large Language Models
Jaehyung Seo, Hyeonseok Moon, Heuiseok Lim
Recent studies on hallucination in large language models (LLMs) have been actively progressing in natural language processing. However, the impact of negated text on hallucination…
KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models
Dongjun Kim, Chanhee Park, Chanjun Park +1
The instruction-following capabilities of large language models (LLMs) are pivotal for numerous applications, from conversational agents to complex reasoning systems. However, curr…
Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models
Hyeonseok Moon, Seongtae Hong, Jaehyung Seo +1
Recent frontier-level LLMs have saturated many previously difficult benchmarks, leaving little room for further differentiation. This progress highlights the need for challenging b…
Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
Dongjun Kim, Gyuho Shim, Yongchan Chun +3
Large Language Models are commonly judged by their scores on standard benchmarks, yet such scores often overstate real capability since they mask the mix of skills a task actually…
TORSO: Template-Oriented Reasoning Towards General Tasks
Minhyuk Kim, Seungyoon Lee, Heuiseok Lim
The approaches that guide Large Language Models (LLMs) to emulate human reasoning during response generation have emerged as an effective method for enabling them to solve complex…
Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning
Sugyeong Eo, Jungjun Lee, Chanjun Park +1
A sparse Mixture-of-Experts (MoE) architecture has emerged as a highly scalable solution by conditionally activating sub-modules without a proportional increase in computational co…
NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models
Hyeonseok Moon, Heuiseok Lim
Recent reports suggest that LLMs can handle increasingly long contexts. However, many existing benchmarks for context understanding embed substantial query-irrelevant content, whic…
Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
Youngjoon Jang, Junyoung Son, Taemin Lee +5
With the increasing utilization of multilingual text information, Cross-Lingual Information Retrieval (CLIR) has become a crucial research area. However, the impact of training dat…
From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
Youngjoon Jang, Seongtae Hong, Junyoung Son +3
Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrati…