Youngjoon Jang

Hi, I’m Youngjoon. I’m a Master’s student in NLP&AI Lab at Korea University, advised by Prof. Heuiseok Lim. Before this, I studied Mechanical Engineering & Computer Science at Hongik University.

I’m drawn to a deceptively simple question: “How can I help people find the right information?” This curiosity drives my work in Information Retrieval, Multilingual Information Retrieval, and Retrieval-Augmented Generation (RAG). My research has been published at SIGIR, ICLR, ACL, and EMNLP, while the Korean retrieval models and benchmarks I led have grown to 250+ GitHub stars and 3M+ downloads on Hugging Face.

I love building in the open, and I actively contribute to projects including Sentence-Transformers, MTEB, and InstructKR.

News

Sep 26, 2026	Our paper “MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol” has been accepted to NeurIPS 2026 Evaluations & Datasets (E&D) Track 🇦🇺
Aug 21, 2026	Our papers MIMO, SHIFT, and SemBridge have been accepted to EMNLP 2026 🇭🇺

Education

Korea University Mar. 2025 – Present

M.S. in Computer Science and Engineering (Advisor: Prof. Heuiseok Lim, NLP&AI Lab)

Hongik University Mar. 2020 – Feb. 2025

B.S. in Computer Engineering & Mechanical and System Design Engineering (Double Major)

Projects

KURE: Korea University Retrieval Models (GitHub · HF · API)
Led the lab's flagship Korean–English retrieval project: built the MTEB-Ko-Retrieval leaderboard and open-sourced the model family with its training and evaluation code (250+ GitHub stars).

Dense & Multi-Vector: KURE-v1 and KURE-v2 both ranked 1st on the leaderboard (as of Aug. 2025 and Oct. 2026, respectively), and KURE-v1 passed 3M downloads. KURE-v2, a multi-vector model, outperforms 8B dense models while being 50× smaller, and the newest KURE-v3 outperforms Qwen3-Embedding-8B while being 7× smaller.
Sparse: KURE-Sparse-{base, nano}, state of the art in Korean sparse retrieval overall and under 0.5B parameters.
Reranker: KURE-Reranker-{base, nano}, state of the art in Korean reranking under 4B and 1B parameters.

ReviewSearch (Blog · GitHub · Demo)
Built and deployed a search engine over 205,988 real peer reviews and rebuttals for agents, so that a rebuttal draft is grounded in how authors actually answered the same concern.

WBL: World Best LLM Project (HF)
Led the data team: built a query-clarity tagging & evaluation framework, and a reward-model-ensemble response-filtering pipeline for large-scale training data.

URACLE–Korea University Collaborative Research
Trained a Korean–English cross-lingual retriever and analyzed language-pair trade-offs. Used model merging to recover monolingual retrieval while retaining cross-lingual retrieval gains. Published in the ACL 2026 MeLLM Workshop.

KT–Korea University Collaborative Research (Korean Legal LLM) (News)
Developed an end-to-end training recipe for a Korean legal-domain LLM, published as LEGALMIDM (ICLR 2026 Data-FM Workshop). Contributed to KT's $10.42M contract for the South Korean Supreme Court AI platform.

Open Source Contributions

Sentence-Transformers 2025 – 2026

Extended the cross-encoder training stack with classic learning-to-rank losses. [PR #6] [PR #7]
Implemented EmbedDistillLoss to support direct embedding-level knowledge distillation. [PR #3665]
Introduced hardness-weighted contrastive learning to up-weight informative hard negatives. [PR #3667]
Implemented CachedSpladeLoss for gradient-cache compatible, memory-efficient SPLADE training. [PR #3670]
Added mergekit-based model merging for dense, sparse, and cross-encoder models. [PR #3776]

MTEB (Massive Text Embeddings Benchmark) 2024 – 2025

Added a Korean retrieval benchmark task to expand multilingual retrieval evaluation. [PR #1388]
Improved stability of the OpenAI embeddings by adding sentence trimming. [PR #1526]
Fixed NaN embeddings for Jasper models by switching model precision. [PR #2481]

InstructKR 2026

Led the Korean Reranker evaluation and leaderboard project. [GitHub]

Publications [International Conference]

NeurIPS 2026 E&D

MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol

Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, and Heuiseok Lim

@inproceedings{jang2026mlaire,
  title = {MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol},
  author = {Jang, Youngjoon and Hong, Seongtae and Moon, Hyeonseok and Lim, Heuiseok},
  year = {2026},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS), Evaluations \& Datasets Track},
}

EMNLP 2026

MIMO: Multilingual Information Retrieval from Monolingual Oracles

Youngjoon Jang, Seongtae Hong, and Heuiseok Lim

@inproceedings{jang2026mimo,
  title = {MIMO: Multilingual Information Retrieval from Monolingual Oracles},
  author = {Jang, Youngjoon and Hong, Seongtae and Lim, Heuiseok},
  year = {2026},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
}

EMNLP 2026 Findings

SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, and Heuiseok Lim

@inproceedings{jang2026shift,
  title = {SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval},
  author = {Jang, Youngjoon and Hong, Seongtae and Moon, Hyeonseok and Lim, Heuiseok},
  year = {2026},
  booktitle = {Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
}

EMNLP 2026

SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridge

Seongtae Hong, Youngjoon Jang, Jia-Huei Ju, Hyeonseok Moon, and Heuiseok Lim

@inproceedings{hong2026sembridge,
  title = {SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridge},
  author = {Hong, Seongtae and Jang, Youngjoon and Ju, Jia-Huei and Moon, Hyeonseok and Lim, Heuiseok},
  year = {2026},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
}

SIGIR 2026

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

Youngjoon Jang, Seongtae Hong, Hyeonseok Moon, and Heuiseok Lim

@inproceedings{jang2026sigir,
  title = {Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval},
  author = {Jang, Youngjoon and Hong, Seongtae and Moon, Hyeonseok and Lim, Heuiseok},
  year = {2026},
  booktitle = {Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},
}

ICLR 2026

Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment

Seongtae Hong, Youngjoon Jang, Jungseob Lee, Hyeonseok Moon, and Heuiseok Lim

@inproceedings{hong2026iclr,
  title = {Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment},
  author = {Hong, Seongtae and Jang, Youngjoon and Lee, Jungseob and Moon, Hyeonseok and Lim, Heuiseok},
  year = {2026},
  booktitle = {Proceedings of the 14th International Conference on Learning Representations (ICLR)},
}

ICLR DATA-FM 2026

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

Youngjoon Jang, Chanhee Park, Hyeonseok Moon, Young-kyoung Ham, Jiwon Moon, Jinhyeon Kim, JuKyung Jung, and Heuiseok Lim

@inproceedings{jang2026legalmidm,
  title = {LEGALMIDM: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model},
  author = {Jang, Youngjoon and Park, Chanhee and Moon, Hyeonseok and Ham, Young-kyoung and Moon, Jiwon and Kim, Jinhyeon and Jung, JuKyung and Lim, Heuiseok},
  year = {2026},
  booktitle = {International Conference on Learning Representations Addressing Data Problems for Foundation Models Workshop (ICLR Data-FM Workshop)},
}

ACL 2026

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

Seungyoon Lee, Minhyuk Kim, Seongtae Hong, Youngjoon Jang, Dongsuk Oh, and Heuiseok Lim

@inproceedings{lee2026clear,
  title = {CLEAR: Cross-Lingual Enhancement in Retrieval via Reverse-training},
  author = {Lee, Seungyoon and Kim, Minhyuk and Hong, Seongtae and Jang, Youngjoon and Oh, Dongsuk and Lim, Heuiseok},
  year = {2026},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL)},
}

ACL MeLLM 2026

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

Youngjoon Jang, Junyoung Son, Taemin Lee, Seongtae Hong, Hyeonseok Moon, Seungyoon Lee, Andrew Matteson, and Heuiseok Lim

@inproceedings{jang2025crosslingual,
  title = {Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging},
  author = {Jang, Youngjoon and Son, Junyoung and Lee, Taemin and Hong, Seongtae and Moon, Hyeonseok and Lee, Seungyoon and Matteson, Andrew and Lim, Heuiseok},
  year = {2026},
  booktitle = {Annual Meeting of the Association for Computational Linguistics Workshop on Multilinguality in the Era of Large Language Models (ACL MeLLM Workshop)},
}

ACL MeLLM 2026

QUERY-SYNERGY: Leveraging High-Resource Languages for Improving Retrieval Performance Across Multiple Languages

Seongtae Hong, Jungseob Lee, Hyeonseok Moon, Seungyoon Lee, Youngjoon Jang, and Heuiseok Lim

@inproceedings{hong2026querysynergy,
  title = {QUERY-SYNERGY: Leveraging High-Resource Languages for Improving Retrieval Performance Across Multiple Languages},
  author = {Hong, Seongtae and Lee, Jungseob and Moon, Hyeonseok and Lee, Seungyoon and Jang, Youngjoon and Lim, Heuiseok},
  year = {2026},
  booktitle = {Annual Meeting of the Association for Computational Linguistics Workshop on Multilinguality in the Era of Large Language Models (ACL MeLLM Workshop)},
}

ACL SRW 2025

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems

Youngjoon Jang, Seongtae Hong, Junyoung Son, Sungjin Park, Chanjun Park, and Heuiseok Lim

@inproceedings{jang2025coreference,
  title = {From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems},
  author = {Jang, Youngjoon and Hong, Seongtae and Son, Junyoung and Park, Sungjin and Park, Chanjun and Lim, Heuiseok},
  year = {2025},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL SRW)},
}

EMNLP 2024

Where am I? Large Language Models Wandering between Semantics and Structures in Long Contexts

Seonmin Koo, Jinsung Kim, Youngjoon Jang, Chanjun Park, and Heuiseok Lim

@inproceedings{koo2024whereami,
  title = {Where am I? Large Language Models Wandering between Semantics and Structures in Long Contexts},
  author = {Koo, Seonmin and Kim, Jinsung and Jang, Youngjoon and Park, Chanjun and Lim, Heuiseok},
  year = {2024},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
}

Publications [Domestic Conference]

HCLT 2025

KURE: Embedding Model for Korean-Specific Retrieval

Youngjoon Jang, Junyoung Son, Taemin Lee, Seongtae Hong, Jungbae Park, and Heuiseok Lim

Best Paper

Best Oral Presentation Award

@inproceedings{jang2025kure,
  title = {KURE: Embedding Model for Korean-Specific Retrieval},
  author = {Jang, Youngjoon and Son, Junyoung and Lee, Taemin and Hong, Seongtae and Park, Jungbae and Lim, Heuiseok},
  year = {2025},
  booktitle = {The 37th Annual Conference on Human \& Cognitive Language Technology (HCLT)},
}

HCLT 2024

KoE5: A New Dataset and Model for Improving Korean Embedding Performance

Youngjoon Jang, Junyoung Son, Taemin Lee, Seongtae Hong, Jungbae Park, and Heuiseok Lim

@inproceedings{jang2024koe5,
  title = {KoE5: A New Dataset and Model for Improving Korean Embedding Performance},
  author = {Jang, Youngjoon and Son, Junyoung and Lee, Taemin and Hong, Seongtae and Park, Jungbae and Lim, Heuiseok},
  year = {2024},
  booktitle = {The 36th Annual Conference on Human \& Cognitive Language Technology (HCLT)},
}

Preprint

Preprint

MixLID: Token-Level Language Identification in Mixed-Language Text

Seongtae Hong, Youngjoon Jang, Seungyoon Lee, Jungseob Lee, and Heuiseok Lim

Under Review

@article{hong2026mixlid,
  title = {MixLID: Token-Level Language Identification in Mixed-Language Text},
  author = {Hong, Seongtae and Jang, Youngjoon and Lee, Seungyoon and Lee, Jungseob and Lim, Heuiseok},
  year = {2026},
  journal = {Under Review},
}

Preprint

RenderRank: Learning to Rerank Text with Compressed Visual Tokens

Seongtae Hong, Youngjoon Jang, Jungseob Lee, Hyeonseok Moon, and Heuiseok Lim

Under Review

@article{hong2026renderrank,
  title = {RenderRank: Learning to Rerank Text with Compressed Visual Tokens},
  author = {Hong, Seongtae and Jang, Youngjoon and Lee, Jungseob and Moon, Hyeonseok and Lim, Heuiseok},
  year = {2026},
  journal = {Under Review},
}

Preprint

Rescaling MLM-Head for Neural Sparse Retrieval

Youngjoon Jang, Seongtae Hong, Jonah Turner, Chanjun Park, and Heuiseok Lim

Under Review

@article{jang2026rescale,
  title = {Rescaling MLM-Head for Neural Sparse Retrieval},
  author = {Jang, Youngjoon and Hong, Seongtae and Turner, Jonah and Park, Chanjun and Lim, Heuiseok},
  year = {2026},
  journal = {Under Review},
}

Preprint

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

Seongtae Hong, Youngjoon Jang, Jungseob Lee, Seungyoon Lee, and Heuiseok Lim

Under Review

@article{hong2026lamar,
  title = {LAMAR: An Open Language-Aware Multilingual Alignment Reranker},
  author = {Hong, Seongtae and Jang, Youngjoon and Lee, Jungseob and Lee, Seungyoon and Lim, Heuiseok},
  year = {2026},
  journal = {Under Review},
}

Preprint

KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval

Yongbin Choi, Gyuho Shim, and Youngjoon Jang^*

Under Review

*Corresponding author

@article{choi2026kovre,
  title = {KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval},
  author = {Choi, Yongbin and Shim, Gyuho and Jang, Youngjoon},
  year = {2026},
  journal = {Under Review},
  note = {*Corresponding author},
}

ArXiv 2025

VAETKI Technical Report

NC-AI Consortium

ArXiv Preprint