2 citations · 5 across the 18 of their papers we have counts for
26 papers
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…
Recovering Off-Policy Supervision for Speculative Decoding
Jungseob Lee, Chanjun Park, Sugyeong Eo +1
Block drafters for speculative decoding are commonly trained on corpora written by external models, where a single off-policy token invalidates supervision for all subsequent slots…
CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters
Jungseob Lee, Sugyeong Eo
Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel. Block drafters score a whole…
Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning
Jungseob Lee, Dongyub Jude Lee, Sugyeong Eo +3
Fine-tuning adapts aligned large language models (LLMs) to downstream tasks, but a few dozen harmful examples can remove their refusal of harmful requests. Prior work localizes saf…
Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding
Jungseob Lee, Seungyoon Lee, Seongtae Hong +2
At each step, decoding one sequence with a large language model rereads the projection weights, whose traffic is fixed, and the key-value (KV) cache, whose traffic grows with conte…
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…
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
Doyun Kim, Chanwoo Kim, Sugyeong Eo +2
LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-…
Beyond Consensus: Downward Bias and Role Asymmetry in Multi-Agent LLM Judges for Subjective Evaluation
Minsoo Song, Chanwoo Kim, Sugyeong Eo +1
Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. However, for subjective rubric-bas…
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…
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…
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…
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…
Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
Sugyeong Eo, Hyeonseok Moon, Evelyn Hayoon Zi +2
Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the appro…
Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline
Seonmin Koo, Chanjun Park, Jinsung Kim +4
Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement o…
Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction
Chanjun Park, Seonmin Koo, Seolhwa Lee +4
Data-centric AI approach aims to enhance the model performance without modifying the model and has been shown to impact model performance positively. While recent attention has bee…
Towards Diverse and Effective Question-Answer Pair Generation from Children Storybooks
Sugyeong Eo, Hyeonseok Moon, Jinsung Kim +6
Recent advances in QA pair generation (QAG) have raised interest in applying this technique to the educational field. However, the diversity of QA types remains a challenge despite…
Self-Improving-Leaderboard(SIL): A Call for Real-World Centric Natural Language Processing Leaderboards
Chanjun Park, Hyeonseok Moon, Seolhwa Lee +3
Leaderboard systems allow researchers to objectively evaluate Natural Language Processing (NLP) models and are typically used to identify models that exhibit superior performance o…
QUAK: A Synthetic Quality Estimation Dataset for Korean-English Neural Machine Translation
Sugyeong Eo, Chanjun Park, Hyeonseok Moon +4
With the recent advance in neural machine translation demonstrating its importance, research on quality estimation (QE) has been steadily progressing. QE aims to automatically pred…
A Self-Supervised Automatic Post-Editing Data Generation Tool
Hyeonseok Moon, Chanjun Park, Sugyeong Eo +3
Data building for automatic post-editing (APE) requires extensive and expert-level human effort, as it contains an elaborate process that involves identifying errors in sentences a…
A New Tool for Efficiently Generating Quality Estimation Datasets
Sugyeong Eo, Chanjun Park, Jaehyung Seo +2
Building of data for quality estimation (QE) training is expensive and requires significant human labor. In this study, we focus on a data-centric approach while performing QE, and…
Automatic Knowledge Augmentation for Generative Commonsense Reasoning
Jaehyung Seo, Chanjun Park, Sugyeong Eo +2
Generative commonsense reasoning is the capability of a language model to generate a sentence with a given concept-set that is based on commonsense knowledge. However, generative l…