Jinsung Kim
Jinsung Kim
Ph.D. Candidate @ NLP & AI Lab., Korea University

About Me

Iโ€™m interested in Natural Language Processing and Deep Learning.
Currently, I am a graduate student and advised by Prof. Heuiseok Lim in the NLP & AI Lab.
Please check my CV ๐Ÿค—!

Contact: jin62304@gmail.com

News

  • 09/2024 โ€œPANDA: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language Modelsโ€ has been accepted to EMNLP 2024.
  • 09/2024 โ€œWhere am I? Large Language Models Wandering between Semantics and Structures in Long Contextsโ€ has been accepted to EMNLP 2024.
  • 09/2024 โ€œSearch if you donโ€™t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Modelsโ€ has been accepted to Findings of EMNLP 2024.

Research Interest

  • Natural Language Processing
  • Dialogue System
  • Information Extraction and Retrieval
  • Large Language Model
  • Deep Learning

Education

  • Korea University (2021/03 - Present)
    • Ph.D. Candidate in Computer Science & Engineering
    • Natural Language Processing and Artificial Intelligence Applications
  • Korea University (2013/03 - 2019/02)
    • B.S Degree Graduate in Spanish Language & Literature
    • Double majored in Language, Brain & Computer (LB & C)

Publications

International Conference

  • PANDA: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language Models
    The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main, Oral Presentation)
    Jinsung Kim, Seonmin Koo, and Heuiseok Lim
  • Where am I? Large Language Models Wandering between Semantics and Structures in Long Contexts
    The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Main)
    Seonmin Koo, Jinsung Kim, YoungJoon Jang, Chanjun Park, and Heuiseok Lim
  • Search if you donโ€™t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models
    The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Findings)
    Seonmin Koo, Jinsung Kim, Chanjun Park, and Heuiseok Lim
  • Revisiting Under-represented Knowledge of Latin American Literature in Large Language Models
    The 27th European Conference on Artificial Intelligence (ECAI 2024 Main, Oral Presentation)
    Jinsung Kim, Seonmin Koo, and Heuiseok Lim
  • KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing
    The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Main)
    Seonmin Koo, Chanjun Park, Jinsung Kim, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, and Heuiseok Lim
  • Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction
    The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Findings)
    Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, and Heuiseok Lim
  • Beyond Candidates : Adaptive Dialogue Agent Utilizing Persona and Knowledge
    The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Findings)
    Jungwoo Lim, Myunghoon Kang, Jinsung Kim, Jeongwook Kim, Yuna Hur, and Heuiseok Lim
  • Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline
    2023 International Conference on Machine Learning โ€“ DataPerf workshop (ICML 2023 Workshop)
    Seonmin Koo, Chanjun Park, Jinsung Kim, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim
  • Towards Diverse and Effective Question-Answer Pair Generation from Children Storybooks
    The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023 Findings)
    Sugyeong Eo, Hyeonseok Moon, Jinsung Kim, Yuna Hur, Jeongwook Kim, and Heuiseok Lim
  • You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona
    The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022 Findings)
    Jungwoo Lim, Myunghoon Kang, Yuna Hur, Seungwon Jung, Jinsung Kim, Yoona Jang, Dongyub Lee, Hyesung Ji, Donghoon Shin, Seungryong Kim, and Heuiseok Lim
  • GRASP: Guiding model with RelAtional Semantics using Prompt
    The 29th International Conference on Computational Linguistics (COLING 2022, Oral Presentation)
    Junyoung Son, Jinsung Kim, Jungwoo Lim, and Heuiseok Lim
  • KoCHET: a Korean Cultural Heritage corpus for Entity-related Tasks
    The 29th International Conference on Computational Linguistics (COLING 2022)
    Gyeongmin Kim, Jinsung Kim, Junyoung Son, and Heuiseok Lim

International Journal

  • A Large-Scale Dataset for Korean Document-level Relation Extraction from Encyclopedia Texts
    Applied Intelligence, vol. 54, pp.8681-8701, 2024
    Suhyune Son, Jungwoo Lim, Seonmin Koo, Jinsung Kim, Younghoon Kim, Youngsik Lim, Dongseok Hyun, and Heuiseok Lim
  • Prompt Language Learner with Trigger Generation for Dialogue Relation Extraction
    Applied Sciences, 13(22), 12414, 2023
    Jinsung Kim, Gyeongmin Kim, Junyoung Son, and Heuiseok Lim
  • A Multi-Faceted Exploration Incorporating Question Difficulty in Knowledge Tracing for English Proficiency Assessment
    Electronics, 12(19), 4171, 2023
    Jinsung Kim, Seonmin Koo, and Heuiseok Lim
  • Enhancing Korean Named Entity Recognition With Linguistic Tokenization Strategies
    IEEE Access, vol. 9, pp. 151814-151823, 2021
    Gyeongmin Kim, Junyoung Son, Jinsung Kim, Hyunhee Lee, and Heuiseok Lim

Domestic Conference

  • Exploring Korean Question Answering Ability of Large Language Model by Question Corruption (์งˆ์˜ ๋ณ€ํ˜•์— ๋”ฐ๋ฅธ ๊ฑฐ๋Œ€ ์–ธ์–ด๋ชจ๋ธ์˜ ํ•œ๊ตญ์–ด ์งˆ์˜์‘๋‹ต ๋Šฅ๋ ฅ ์—ฐ๊ตฌ)
    The 36th Annual Conference on Human & Cognitive Language Technology (HCLT 2024, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Jinsung Kim, Seonmin Koo, Kinam Park, and Heuiseok Lim
  • Examining the Ability of Large Language Model on Entity-Based Korean Question-Answering (์—”ํ‹ฐํ‹ฐ ๊ธฐ๋ฐ˜ ์ถ”๋ก ์„ ํ†ตํ•œ ๊ฑฐ๋Œ€ ์–ธ์–ด ๋ชจ๋ธ์˜ ํ•œ๊ตญ์–ด ์งˆ์˜์‘๋‹ต ๋Šฅ๋ ฅ ์—ฐ๊ตฌ)
    The 36th Annual Conference on Human & Cognitive Language Technology (HCLT 2024, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Seonmin Koo, Jinsung Kim, Chanjun Park, Kinam Park, and Heuiseok Lim
  • Mixture of Models: Towards Effective Domain Expert Ensemble of Large Language Models (Mixture of Models: ๊ฑฐ๋Œ€ ์–ธ์–ด๋ชจ๋ธ ๊ธฐ๋ฐ˜ ํšจ๊ณผ์  ๋„๋ฉ”์ธ ์ „๋ฌธ๊ฐ€ ์•™์ƒ๋ธ” ๊ธฐ๋ฒ• ์—ฐ๊ตฌ)
    The 36th Annual Conference on Human & Cognitive Language Technology (HCLT 2024, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Kyuho Shim, Sugyeong Eo, Jinsung Kim, Seongtae Hong, Sangyoon Jun, Hoondong Kim, and Heuiseok Lim
  • A Comparative Study on Korean Zero-shot Relation Extraction using a Large Language Model (๊ฑฐ๋Œ€ ์–ธ์–ด ๋ชจ๋ธ์„ ํ™œ์šฉํ•œ ํ•œ๊ตญ์–ด ์ œ๋กœ์ƒท ๊ด€๊ณ„ ์ถ”์ถœ ๋น„๊ต ์—ฐ๊ตฌ)
    The 35th Annual Conference on Human & Cognitive Language Technology (HCLT 2023, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Jinsung Kim, Gyeongmin Kim, Kinam Park, and Heuiseok Lim
  • Cross-document Relation Extraction using Bridging Context Identification (์ค‘๊ฐ„ ๋ฌธ๋งฅ ์‹๋ณ„ ๋ฐ ๊ฒ€์ƒ‰์„ ํ™œ์šฉํ•œ ๋ฌธ์„œ๊ฐ„ ๊ด€๊ณ„ ์ถ”์ถœ)
    The 35th Annual Conference on Human & Cognitive Language Technology (HCLT 2023, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, Aram So, and Heuiseok Lim
  • An Empirical Study on the Length Granularity in Long-Form Question Answering
    The 18th Asia Pacific International Conference on Information Science and Technology (APIC-IST 2023, Best Paper)
    Hyeonseok Moon, Jinsung Kim, Kinam Park, Jeongbae Park, and Heuiseok Lim
  • Domain-specific Korean Relation Extraction system using Prompt with Meta-Information (๋ฉ”ํƒ€ ์ •๋ณด๋ฅผ ํ™œ์šฉํ•œ ํ”„๋กฌํ”„ํŠธ ๊ธฐ๋ฐ˜ ๋„๋ฉ”์ธ ํŠนํ™” ํ•œ๊ตญ์–ด ๊ด€๊ณ„ ์ถ”์ถœ)
    The 34th Annual Conference on Human & Cognitive Language Technology (HCLT 2022, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Jinsung Kim, Gyeongmin Kim, Junyoung Son, Aram So, and Heuiseok Lim
  • Methodology of Trigger Generation optimized for Dialogue Relation Extraction task (๋Œ€ํ™”ํ˜• ๊ด€๊ณ„ ์ถ”์ถœ ํƒœ์Šคํฌ์— ์ตœ์ ํ™”๋œ ํŠธ๋ฆฌ๊ฑฐ ์ƒ์„ฑ ๋ฐฉ๋ฒ•๋ก  )
    The 34th Annual Conference on Human & Cognitive Language Technology (HCLT 2022, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Gyeongmin Kim, Junyoung Son, Jinsung Kim, Jaechoon Jo, and Heuiseok Lim
  • An Analysis of Named Entity Recognition System using MLM-based Language Transfer Learning (MLM ๊ธฐ๋ฐ˜ ์–ธ์–ด ๊ฐ„ ์ „์ดํ•™์Šต์„ ์ด์šฉํ•œ ๊ฐœ์ฒด๋ช… ์ธ์‹ ๋ฐฉ๋ฒ•๋ก  ๋ถ„์„)
    The 34th Annual Conference on Human & Cognitive Language Technology (HCLT 2022, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Junyoung Son, Gyeongmin Kim, Jinsung Kim, Yuna Hur, and Heuiseok Lim
  • Dialogue Relation Extraction using Dialogue Graph (์ƒํ˜ธ์ฐธ์กฐ ์ •๋ณด์™€ ๋Œ€ํ™” ๊ทธ๋ž˜ํ”„๋ฅผ ํ™œ์šฉํ•œ ๋Œ€ํ™” ๊ด€๊ณ„์ถ”์ถœ ๋ชจ๋ธ )
    The 34th Annual Conference on Human & Cognitive Language Technology (HCLT 2022, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Jungwoo Lim, Junyoung Son, Jinsung Kim, Yuna Hur, Jaehyung Seo, Yoonna Jang, Jeongbae Park, and Heuiseok Lim
  • An Effective Segmentation Scheme for Korean Sentence Classification tasks (ํ•œ๊ตญ์–ด ๋ฌธ์žฅ ๋ถ„๋ฅ˜ ํƒœ์Šคํฌ์—์„œ์˜ ํšจ๊ณผ์  ๋ถ„์ ˆ ์ „๋žต )
    The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2021, ํ•œ๊ธ€ ๋ฐ ํ•œ๊ตญ์–ด์ •๋ณด์ฒ˜๋ฆฌ ํ•™์ˆ ๋Œ€ํšŒ)
    Jinsung Kim, Gyeongmin Kim, Junyoung Son, and Heuiseok Lim

Domestic Journal

  • A Comparative study on the Effectiveness of Segmentation Strategies for Korean Word and Sentence Classification tasks (ํ•œ๊ตญ์–ด ๋‹จ์–ด ๋ฐ ๋ฌธ์žฅ ๋ถ„๋ฅ˜ ํƒœ์Šคํฌ๋ฅผ ์œ„ํ•œ ๋ถ„์ ˆ ์ „๋žต์˜ ํšจ๊ณผ์„ฑ ์—ฐ๊ตฌ)
    Journal of the Korea Convergence Society (ํ•œ๊ตญ์œตํ•ฉํ•™ํšŒ), Volume 12 Issue 12, Pages.39-47, 2021
    Jinsung Kim, Gyeongmin Kim, Junyoung Son, Jeongbae Park, and Heuiseok Lim