Kwangwook Seo

PhD student, Artificial Intelligence, Yonsei University

Joined

February 2024

Names

Kwangwook Seo (Preferred)

KwangWook Seo

Emails

****@yonsei.ac.kr (Confirmed)

Personal Links

Career & Education History

PhD student

Artificial Intelligence, Yonsei University (yonsei.ac.kr)

2023 – 2028

Advisors, Relations & Conflicts

PhD Advisor

Dongha Lee

Present

Expertise

Knowledge Augmentation of LLMs

Present

Personalized Agents and User Simulation

Present

Table Reasoning

Present

Personalized Reward Modeling

Present

Publications

In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners
Jaehoon Kim, Kwangwook Seo, Dongha Lee
- Submitted to ICLR 2026
- Readers: Everyone
BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
Hyunseo Kim, Sangam Lee, Kwangwook Seo, Dongha Lee
- Submitted to ICLR 2026
- Readers: Everyone
MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables
Kwangwook Seo, Donguk Kwon, Dongha Lee
- CoRR 2025
- Readers: Everyone
Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization
Kwangwook Seo, Jinyoung Yeo, Dongha Lee
- EMNLP (Findings) 2024
- Readers: Everyone
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models
Seoyeon Kim, Kwangwook Seo, Hyungjoo Chae, Jinyoung Yeo, Dongha Lee
- ACL (1) 2024
- Readers: Everyone
Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems
Sunghwan Kim, Tongyoung Kim, Kwangwook Seo, Jinyoung Yeo, Dongha Lee
- CoRR 2024
- Readers: Everyone

Kwangwook Seo

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners

BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback

MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables

Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization

VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models

Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems

Co-Authors