* indicates equal contribution among authors
† indicates co-corresponding authors
2025
-
Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
Kyungmin Min , Minbeom Kim , Kang-il Lee , Dongryeol Lee , and Kyomin Jung
NAACL 2025 (Findings) , Apr 2025
-
Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
Dongryeol Lee , Minwoo Lee , Kyungmin Min , Joonsuk Park† , and Kyomin Jung†
COLING 2025 (Oral) , Jan 2025
2024
-
Mitigating Hallucinations in LVLMs via Summary-Guided Decoding
Kyungmin Min , Minbeom Kim , Kang-il Lee , Dongryeol Lee , and Kyomin Jung
Neurips Safe Generative AI Workshop 2024 , Dec 2024
2023
-
Leveraging Ensemble Techniques and Metadata for Subjective Knowledge-grounded Conversational Systems
Seongho Joo* , Kang-il Lee* , Kyungmin Min* , Joongbo Shin , Janghoon Han , Seungpil Won , and Kyomin Jung
The Eleventh Dialog System Technology Challenge (DSTC11) , Sep 2023
The goal of DSTC11 track 5 is to build task-oriented dialogue systems that can effectively utilize external knowledge sources such as FAQs and reviews. This year’s challenge differs from previous ones as it includes subjective knowledge snippets and requires multiple snippets for a single turn. We propose a pipeline system for the challenge focusing on entity tracking, knowledge selection and response generation. Specifically, we devise a novel heuristic to ensemble the outputs from the rule-based method and neural model for entity tracking and knowledge selection. We also leverage metadata information in the knowledge source to handle fine-grained user queries. Our approach achieved the first place in objective evaluation and the third place in human evaluation of DSTC11 track 5.