2 citations · 5 across the 32 of their papers we have counts for
15 papers · 1 filter
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…
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…
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…
Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks
Dongyub Jude Lee, Jungseob Lee, Chanjun Park +2
Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error rate among served answers. We…
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…
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…
MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal
Youngjoon Jang, Seongtae Hong, Hyeonseok Moon +1
Multilingual Information Retrieval is increasingly important in real-world search settings, where users issue queries over mixed-language corpora. Existing evaluations mainly rewar…
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 Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
Jeongho Yoon, Chanhee Park, Yongchan Chun +2
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unautho…
Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment
Seongtae Hong, Youngjoon Jang, Jungseob Lee +2
With the increasing accessibility and utilization of multilingual documents, Cross-Lingual Information Retrieval (CLIR) has emerged as an important research area. Conventionally, C…