Seungyeon Jwa

M.S./Ph.D. at Seoul National University, advised by Prof. Jonghyun Choi. Currently visiting Minnesota NLP Group hosted by Prof. Dongyeop Kang (Apr–Oct 2026). Research focuses on evaluation and alignment of foundation models.

email|publications|news|github|cv
Selected Publications
evaluation
Becoming Experienced Judges: Selective Test-Time Learning for Evaluators
Seungyeon Jwa, Daechul Ahn, Reokyoung Kim, Dongyeop Kang, Jonghyun Choi
EACL 2026 (Short) · EvalEval @ ACL 2026 Oral ×2
paper extended code
evaluation alignment
OffsetBias: Leveraging Debiased Data for Tuning Evaluators
Junsoo Park*, Seungyeon Jwa*, Meiying Ren, Daeyoung Kim, Sanghyuk Choi
Findings of EMNLP 2024
paper code 🤗 collection model dataset blog
alignment
Mitigating Hate Speech in Korean Open-domain Chatbot using CTRL
Seungyeon Jwa*, Young-rok Cha*, Moonsu Han, Donghoon Shin
HCLT 2021
paper
News
Jun 2026 Our paper on benchmarking AudioLLMs as paralinguistic judges, ParaPairAudioBench, was accepted to Interspeech 2026. This work was done during my AI residency at NAVER Cloud.
Apr 2026 I started visiting at Minnesota NLP Group, hosted by Prof. Dongyeop Kang (Apr–Oct 2026).
Apr 2026 LWE was also accepted to ACL EvalEval Workshop as Oral.
more →