7 citations · 18 across the 50 of their papers we have counts for
57 papers
Evaluating Compressed Memory: Dependence, Utility, and Content Benefit
Minsu Oh, Seunghui Jwa, Chanjun Park +1
Does a language model answer better because its compressed memory contains useful document information? Replacing memory vectors with zeros can lower a trained model's score withou…
Shared Stopping Decisions Change Answers in HQQ Cache Quantization
Seunghui Jwa, Minsu Oh, Chanjun Park +1
Language-model systems batch questions for throughput, but unrelated questions should not change a target's answer when its input and numerical execution are fixed. We study compre…
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…
Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models
Jeongho Yoon, Chanhee Park, Yongchan Chun +5
Cloud-based large language models (LLMs) require users to disclose plaintext data to service providers, creating privacy risks in sensitive domains. Existing privacy-preserving app…
The Blindness of Document-Level Translation Evaluation
Ahrii Kim, Vilém Zouhar, Chanjun Park +1
Document-level machine translation (MT) evaluation extends segment-level protocols by presenting full documents to annotators, on the assumption that such presentation elicits docu…
Discourse Dependency: A Continuous Criterion for Translation Difficulty
Ahrii Kim, Chanjun Park, Seong-heum Kim
Recent calls for harder machine translation benchmarks have not clarified what difficulty should mean. We argue that one meaningful and currently unmeasured axis is referential rea…
Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents
Seonghyeon Cho, Chanjun Park
Large Language Model (LLM) agents increasingly rely on external skills, yet standard evaluations obscure whether retrieving these skills actually helps. Aggregate metrics often com…
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…
Auditing MCQA Benchmarks through Probability Landscapes
Minsoo Song, Chanjun Park
As Large Language Models rapidly advance, performance on standard multiple-choice question answering (MCQA) benchmarks is reaching saturation. While the community has responded by…
To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG
Jungseob Lee, Chanjun Park, Heuiseok Lim
Multi-agent document assessment for retrieval-augmented generation is computationally expensive, driving practitioners toward smaller, deployable models whose assessment mechanisms…
Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards
Jungseob Lee, Seungyoon Lee, Seongtae Hong +3
Training large language models to reason efficiently is a critical challenge. While integrating length-penalizing rewards into Group Relative Policy Optimization (GRPO) aims to red…
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…
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…
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…
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…
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…
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…
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…
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
Yongchan Chun, Minhyuk Kim, Dongjun Kim +2
Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large l…
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…
MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation
Chanhee Park, Hyeonseok Moon, Chanjun Park +1
Retrieval-Augmented Generation (RAG) has gained prominence as an effective method for enhancing the generative capabilities of Large Language Models (LLMs) through the incorporatio…
FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models
Dahyun Jung, Seungyoon Lee, Hyeonseok Moon +2
Recent advancements in Large Language Models (LLMs) have significantly enhanced interactions between users and models. These advancements concurrently underscore the need for rigor…