Award

Nrf-2021r1a6a1a03045425

Funder: National Research Foundation of Korea

Funded outputs count: 83

Funder award ID: NRF-2021R1A6A1A03045425

OpenAlex ID: G6181273566

ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models

2026 · Kang, Myunghoon, Lee, Jungseob, et al. · arXiv (Cornell University)

Generalizable Lifelong Model Editing via Preference Optimization

2026 · Jung, Dahyun, Son, Suhyune, et al. · arXiv (Cornell University)

The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice

2026 · Lee, Jungseob, Seo, Jaehyung, et al. · arXiv (Cornell University)

Language Chain in Alignment: Cross-lingual Ranking Preference Optimization

2026 · Lee, Seungyoon, Kim, Minhyuk, et al. · arXiv (Cornell University)

Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses

2026 · Eo, Sugyeong, Lim, Heuiseok · arXiv (Cornell University)

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering

2026 · Shin, Joongmin, Shim, Gyuho, et al. · arXiv (Cornell University)

LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model

2026 · Jang, Youngjoon, Park, Chanhee, et al. · arXiv (Cornell University)

Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment

2026 · Hong, Seongtae, Jang, Youngjoon, et al. · arXiv (Cornell University)

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval

2026 · Jang, Youngjoon, Hong, Seongtae, et al. · arXiv (Cornell University)

Can Small Open-Source Language Models With Retrieval-Augmented Generation Match GPT-4 Performance in Breast Cancer Clinical Decision Support?

2026 · Chanhee Park, In Hae Park, et al. · JCO Clinical Cancer Informatics

Code Redteaming: Probing Ethical Sensitivity of LLMs Through Natural Language Embedded in Code

2026 · Chanjun Park, Jeongho Yoon, et al. · Mathematics

Exploring Coding Spot: Understanding Parametric Contributions to LLM Coding Performance

2026 · Dongjun Kim, Minhyuk Kim, et al.

I Know, but I Don’t Know! How Persona Conflict Undermines Instruction Adherence in Large Language Models

2026 · Seonmin Koo, Jinsung Kim, et al. · Findings of the Association for Computational Linguistics: EACL

LangSAE Editing: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal

2026 · Dongjun Kim, Jeongho Yoon, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)

Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging

2026 · Youngjoon Jang, Junyoung Son, et al.

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering

2026 · Joongmin Shin, Gyuho Shim, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)

CLEAR: Cross-Lingual Enhancement in Retrieval via Reverse-training

2026 · Seungyoon Lee, Minhyuk Kim, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)

I Don’t Need Solution. I Need Emotional Support : Empathetic LLMs based on Emotional Validation

2026 · Suhyune Son, Jungwoo Lim, et al.

NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models

2026 · Hyeonseok Moon, Heuiseok Lim

EASE: Entity-Aware Sub-table Generation for Real-world Multi-table QA

2026 · Myunghoon Kang, Dahyun Jung, et al. · Annual Meeting of the Association for Computational Linguistics (ACL)

Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses

2026 · Sugyeong Eo, Heuiseok Lim · Annual Meeting of the Association for Computational Linguistics (ACL)

Query-Synergy: Leveraging High-Resource Languages for Improving Retrieval Performance Across Multiple Languages

2026 · Seongtae Hong, Jungseob Lee, et al.

CoME: An Unlearning-based Approach to Conflict-free Model Editing

2025 · Dahyun Jung, Jaehyung Seo, et al. · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL) · 1

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents

2025 · Jeiyoon Park, Chanjun Park, et al. · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL) · 2

Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models

2025 · Hyeonseok Moon, Jaehyung Seo, et al. · Findings of the Association for Computational Linguistics: NAACL · 2