Sukmin Cho

nelllpic@kaist.ac.kr

I am PhD student in Computer Science at Korea Institute of Advanced Science and Technology (KAIST). My research interest pertains to analyzing the impact of input prompt on Large Language Models (LLMs) and identifying the optimal prompts for aligning LLMs under diverse conditions.

Database-Augmented Query Representation for Information Retrieval
Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C. Park
EMNLP'25 | Conference on Empirical Methods in Natural Language Processing
pdf| abstract|

The RAG paradox: A black-box attack exploiting unintentional vulnerabilities in retrieval-augmented generation systems
Chanwoo Choi, Jinsoo Kim, Sukmin Cho, Soyeong Jeong, and Buru Chang
Findings of EMNLP'25 | Conference on Empirical Methods in Natural Language Processing
pdf| abstract|

Upcycling Candidate Tokens of Large Language Models for Query Expansion
Jinseok Kim, Sukmin Cho, Soyeong Jeong, Sangyeop Kim and Sungzoon Cho
CIKM'25 | Conference on Information and Knowledge Management
To appear

Temporal Information Retrieval via Time-Specifier Model Merging
SeungYoon Han, Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, Huije Lee, and Jong C. Park
KnowFM@ACL'25 | Towards Knowledgeable Foundation Models
pdf| abstract|

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, SeungYoon Han, and Jong C. Park
Findings of ACL'25 | Annual Meeting of the Association for Computational Linguistics
pdf| abstract|

Does Rationale Quality Matter? Enhancing Mental Disorder Detection via Selective Reasoning Distillation
Hoyun Song, Huije Lee, Jisu Shin, Sukmin Cho, Changgeon Ko, and Jong C. Park
Findings of ACL'25 | Annual Meeting of the Association for Computational Linguistics
pdf| abstract|

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Sukmin Cho, Sangjin Choi, Taeho Hwang, Jeongyeon Seo, Soyeong Jeong, Huije Lee, Hoyun Song, Jong C. Park, and Youngjin Kwon
Findings of NAACL'25 | Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics
pdf| abstract|

An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs
Euijun Hwang, Sukmin Cho, Junmyeong Lee, and Jong C. Park
NAACL'25 | Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics
pdf| abstract|

A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production
Euijun Hwang, Sukmin Cho, Junmyeong Lee, and Jong C. Park
WACV'25 | IEEE/CVF Winter Conference on Applications of Computer Vision
pdf| abstract|

PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling
Junmyeong Lee, Euijun Hwang, Sukmin Cho, and Jong C. Park
SSL@NeurIPS'24 | Self-Supervised Learning - Theory and Practice
pdf| abstract|

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations
Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang and Jong C. Park
Findings of EMNLP'24 | Conference on Empirical Methods in Natural Language Processing
pdf| abstract|

Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling
Huije Lee, Hoyun Song, Jisu Shin, Sukmin Cho, SeungYoon Han and Jong C. Park
Findings of EMNLP'24 | Conference on Empirical Methods in Natural Language Processingg
pdf| abstract|

DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation
Taeho Hwang, Soyeong Jeong, Sukmin Cho, SeungYoon Han and Jong C. Park KnowledgeNLP@ACL'24 | 3rd Workshop on Knowledge-Augmented NLP
pdf| abstract|

Preprocessing Mediapipe Keypoints with Keypoint Reconstruction and Anchors for Isolated Sign Language Recognition
Kyunggen Roh, Huije Lee, Eui Jun Hwang, Sukmin Cho, and Jong C. Park
sign-lang@LREC-COLING'24 | 11th Workshop on the Representation and Processing of Sign Languages: Evaluation of Sign Language Resources
pdf| abstract| cite|

Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang and Jong C. Park NAACL'24 | Annual Conference of the North American Chapter of the Association for Computational Linguistic
pdf| abstract|

Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering
Sukmin Cho, Jeongyeon Seo, Soyeong Jeong and Jong C. Park Findings of EMNLP'23 | Conference on Empirical Methods in Natural Language Processing
pdf| abstract| cite|

Test-Time Self-Adaptive Small Language Models for Question Answering
Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang and Jong C. Park Findings of EMNLP'23 | Conference on Empirical Methods in Natural Language Processing
pdf| abstract| cite|

Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker
Sukmin Cho, Soyeong Jeong, Jeongyeon Seo and Jong C. Park Findings of ACL'23 | Annual Conference of Computational Linguistics
pdf| abstract| cite|

Sign language production with avatar layering: A critical use case over rare words
Jung-Ho Kim, Eui Jun Hwang, Sukmin Cho, Du Hui Lee and Jong C. Park LREC'22 | International Conference on Language Resources and Evaluation
pdf| abstract| cite|

Query generation with external knowledge for dense retrieval
Sukmin Cho, Soyeong Jeong, Wonsuk Yang and Jong C. Park DeeLIO@ACL'22 | Deep Learning Inside Out
pdf| abstract| cite|

Augmenting document representations for dense retrieval with interpolation and perturbation
Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang and Jong C. Park ACL'22 | Annual Conference of the Association for Computational Linguistics
pdf| abstract| cite|