2 citations · 2 across the 22 of their papers we have counts for
30 papers
MixLID: Token-Level Language Identification in Mixed-Language Text
Seongtae Hong, Youngjoon Jang, Seungyoon Lee +2
Processing multilingual text requires both identifying a broad range of languages and distinguishing the language of each token in inputs containing multiple languages. We introduc…
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…
RenderRank: Learning to Rerank Text with Compressed Visual Tokens
Seongtae Hong, Youngjoon Jang, Jungseob Lee +2
Rendering document text as images allows vision-language models to encode documents as visual tokens, which can reduce input sequence length compared with text input. This reductio…
AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
Chanhee Park, Jeongho Yoon, Sungbin Han +2
Agentic tasks require a large language model to interact with the world, navigating information and gathering evidence across multiple steps with restricted resources. Due to this…
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…
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…
Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs
Kisu Yang, Yoonna Jang, Heuiseok Lim
Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the reserved identifiers the model…
Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
Seungyoon Lee, Minhyuk Kim, Jungseob Lee +1
The alignment of Large Language Models heavily relies on English-centric high-quality preference data, which often leads to suboptimal performance in other languages. In this paper…
HealMed: Multilingual Evaluation of Large Language Models in Medicine
Yingjian Chen, Fan Gao, Sherry T. Tong +42
We present HealMed, an expert-reviewed benchmark for multilingual evaluation of large language models in medicine. HealMed contains 1,000 examples in each of nine languages, drawn…
Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning
Chanhee Park, Sungbin Han, Jeongho Yoon +2
Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deploym…
Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents
Jiwon Jang, Kisu Yang, Heuiseok Lim +1
Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling agents, where it now matters most. On -be…
LAMAR: An Open Language-Aware Multilingual Alignment Reranker
Seongtae Hong, Youngjoon Jang, Jungseob Lee +2
In multilingual retrieval augmented generation pipelines, an embedding model can retrieve relevant documents written in multiple languages, which are subsequently reranked before a…
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…
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…
Rescaling MLM-Head for Neural Sparse Retrieval
Youngjoon Jang, Seongtae Hong, Jonah Turner +1
Learned sparse retrieval (LSR) models such as SPLADE have traditionally used BERT-style masked language models as backbone encoders. A natural expectation is that replacing BERT wi…
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…
SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
Youngjoon Jang, Seongtae Hong, Hyeonseok Moon +1
With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access. MLIR enables…
SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges
Seongtae Hong, Youngjoon Jang, Jia-Heui Ju +2
Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to languag…
Llamion Technical Report
Kisu Yang, Yoonna Jang, Hyeonseok Moon +6
We release Llamion, a family of 14B-parameter open-weight language models obtained by transforming Orion-14B into the standardized Llama-family architecture. The transformation is…
MIMO: Multilingual Information Retrieval via Monolingual Objectives
Youngjoon Jang, Seongtae Hong, Heuiseok Lim
Multilingual Information Retrieval (MLIR) reflects real-world search environments in which queries and relevant documents may appear in different languages within a mixed-language…
LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model
Youngjoon Jang, Chanhee Park, Hyeonseok Moon +5
In recent years, the rapid proliferation of open-source large language models (LLMs) has spurred efforts to turn general-purpose models into domain specialists. However, many domai…
Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval
Youngjoon Jang, Seongtae Hong, Hyeonseok Moon +1
Transferring knowledge from a cross-encoder teacher via Knowledge Distillation (KD) has become a standard paradigm for training retrieval models. While existing studies have largel…
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
Dahyun Jung, Jaewook Lee, Heuiseok Lim
Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged a…