publications

J: Journal, C: Conference, W: Workshop, A: Arxiv Preprint, T: Tech Report, D: Dissertation, P: Patent \ * indicates equal contribution among authors
† indicates co-corresponding authors

2025

[A3] Drift: Decoding-time Personalized Alignments with Implicit User Preferences
[C27] Code-Switching Curriculum Learning for Multilingual Transfer in LLMs
[C26] CSRT: Evaluation and Analysis of LLMs using Code-Switching Red-Teaming Dataset
[C25] AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
[C24] MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty
[C23] Guaranteed Generation from Large Language Models

2024

[C22] BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
  • Junho Myung*, Nayeon Lee*, Yi Zhou*, Jiho Jin, Rifki Afina Putri, Dimosthenis Antypas, Hsuvas Borkakoty, Eunsu Kim, Carla Perez-Almendros, Abinew Ali Ayele, Víctor Gutiérrez-Basulto, Yazmín Ibáñez-García, Hwaran Lee, Shamsuddeen Hassan Muhammad, Kiwoong Park, Anar Sabuhi Rzayev, Nina White, Seid Muhie Yimam, Mohammad Taher Pilehvar, Nedjma Ousidhoum, Jose Camacho-Collados, Alice Oh
  • Cross-Cultural Considerations in NLP workshop @ ACL 2024 (Best paper)
  • NeurIPS Dataset & Benchmark Track, 2024
[T1] HyperCLOVA X Technical Report
  • HyperCLOVA X Team, NAVER Cloud
  • Role as a Safety Leader
  • Arxiv, 2024
[C21] TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models
  • Jaewoo Ahn, Taehyun Lee, Junyoung Lim, Jin-Hwa Kim, Sangdoo Yun, Hwaran Lee, Gunhee Kim
  • ACL Findings, 2024
[C20] Calibrating Large Language Models Using Their Generations Only
  • Dennis Thomas Ulmer, Martin Gubri, Hwaran Lee, Sangdoo Yun, Seong Joon Oh
  • ACL, 2024
[C19] TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
  • Martin Gubri, Dennis Thomas Ulmer, Hwaran Lee, Sangdoo Yun, Seong Joon Oh
  • ACL Findings, 2024
[C18] KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge
  • Jiyoung Lee, Minwoo Kim, Seungho Kim, Junghwan Kim, Seunghyun Won, Hwaran Lee, Edward Choi
  • ACL Findings, 2024
  • project page
[C17] Who Wrote this Code? Watermarking for Code Generation
  • Taehyun Lee*, Seokhee Hong*, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin†, Gunhee Kim†
  • ACL, 2024
[C16] LifeTox: Unveiling Implicit Toxicity in Life Advice
  • Minbeom Kim, Jahyun Koo, Hwanhee Lee, Joonsuk Park, Hwaran Lee, Kyomin Jung
  • NAACL (Short), 2024
[C15, W6] Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
  • Seungone Kim*, Jamin Shin*, Yejin Cho*, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, Minjoon Seo
  • ICLR, 2024
  • Instruction Workshop @ NeurIPS 2023
  • code & datset
[J7] KoBBQ: Korean Bias Benchmark for Question Answering

2023

[C14] ProPILE: Probing Privacy Leakage in Large Language Models
  • Siwon Kim, Sangdoo Yun, Hwaran Lee, Martin Gubri, Sungroh Yoon, Seong Joon Oh
  • NeurIPS (Spotlight), 2023
[C13] KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applications
  • Hwaran Lee*, Seokhee Hong*, Joonsuk Park, Takyoung Kim, Gunhee Kim, and Jung-Woo Ha
  • ACL (Industrial Track), 2023
  • code & dataset
[C12] SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created through Human-Machine Collaboration
  • Hwaran Lee*, Seokhee Hong*, Joonsuk Park, Takyoung Kim, Meeyoung Cha, Yejin Choi, Byoungpil Kim, Gunhee Kim, Eun-Ju Lee, Yong Lim, Alice Oh, Sangchul Park and Jung-Woo Ha
  • ACL, 2023 (Oral, Best Paper Nominated)
  • code & dataset
[C11] Query-Efficient Black-Box Red Teaming via Bayesian Optimization
  • Deokjae Lee, JunYeong Lee, Jung-Woo Ha, Jin-Hwa Kim, Sang-Woo Lee, Hwaran Lee and Hyun Oh Song
  • ACL, 2023
  • code
[C10] Critic-Guided Decoding for Controlled Text Generation
  • Minbeom Kim, Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee†, Kyomin Jung†
  • ACL Findings, 2023
  • code
[C9] ClaimDiff: Comparing and Contrasting Claims on Contentious Topics
  • Miyoung Ko, Ingyu Seong, Hwaran Lee, Joonsuk Park, Minsuk Chang, Minjoon Seo
  • ACL Findings, 2023
  • dataset

2022

[W5] Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate - from the Perspective of DistilBERT
  • Jaimeen Ahn, Hwaran Lee, Jin-Hwa Kim, Alice Oh
  • In Proceedings of the 4rd Workshop on Gender Bias in Natural Language Processing (@ NAACL workshop), 2022
[C8] Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking
  • Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee†, Kyomin Jung†
  • NAACL Findings, 2022
[C7] Plug-and-Play Adaptation for Continuously-updated QA
  • Kyungjae Lee, Wookje Han, Seung-won Hwang, Hwaran Lee, Joonsuk Park, Sang-Woo Lee
  • ACL Findings, 2022
[C6] TaleBrush: Sketching Stories with Generative Pretrained Language Models
  • John Yoon Young Chung, Wooseok Kim, Kang Min Yoo, Hwaran Lee, Eytan Adar, Minsuk Chang
  • CHI, 2022
  • video
[W4] TaleBrush: Visual Sketching of Story Generation with Pretrained Language Models
  • John Yoon Young Chung, Wooseok Kim, Kang Min Yoo, Hwaran Lee, Eytan Adar, Minsuk Chang
  • CHI EA ‘22: CHI Conference on Human Factors in Computing Systems Extended Abstracts

2020-2021

[J6] SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
  • Hwaran Lee, Seokhwan Jo, HyungJun Kim, Sangkeun Jung, and Tae-Yoon Kim
  • IEEE Access (IF=3.9), 2021
  • pdf | code
[C5] Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer
  • Gi-Cheon Kang, Junseok Park, Hwaran Lee, Byoung-Tak Zhang, and Jin-Hwa Kim
  • EMNLP Findings, 2021
  • code
[P2] Method and Apparatus for Providing Hybrid Intelligent Customer Consultation
  • Tae-Yoon Kim, Jin Kim, Hyungjoon Kim, Jinsik Lee, Hwaran Lee, Heewon Jeon, Seokhwan Jo
  • KR Patent KR102488886B1, filed March 2022 and issued January 2023
[P1] Method and Apparatus for Dialogue State Tracking for Use in Goal-oriented Dialog System
  • Hwaran Lee, Jinsik Lee, Tae-Yoon Kim
  • KR Patent KR102281581B1, filed July 2019 and issued July 2021
  • CN Patent CN114127711A, filed July 2020
  • WO Patent WO2021010636A1, filed July 2020
  • US Patent US11687731B2, filed July 2020 and issued Jan 2021

2019

[C4] SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
  • Hwaran Lee*, Jinsik Lee*, and Tae-Yoon Kim
  • ACL, 2019
  • code | poster
[J5] Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
  • Geonmin Kim, Hwaran Lee, Bo-Kyeong Kim, Sang-Hoon Oh, and Soo-Young Lee
  • IEEE Signal Processing Letters (SPL), 2019.
  • pdf | code

2018

[D] Neural representations for speech recognition and natural language generation
  • Hwaran Lee
  • Ph.D. Dissertation, Korea Advanced Institute of Science and Technology (KAIST), 2018.
[J4] Rescoring of N-best Hypotheses using Top-down Selective Attention for Automatic Speech Recognition
  • Ho-Gyeong Kim, Hwaran Lee, Geonmin Kim, Sang-Hoon Oh, and Soo-Young Lee
  • IEEE Signal Processing Letters (SPL), 2018.
  • pdf

2017

[W3] A Deep Chatbot for QA and Chitchat
  • Geonmin Kim*, Hwaran Lee*, CheongAn Lee, Eunmi Hong, Byunggeun Kim, and Soo-Young Lee (team kAIb)
  • The Conversational Intelligence Challenge section on NIPS 2017 Competition Track Workshop (ConvAI, NIPS), 2017.
  • Ranked 3rd |pdf | code | poster
[C3] Compositional Sentence Representation from Character within Large Context Text
  • Geonmin Kim, Hwaran Lee, Bo-Kyeong Kim, and Soo-Young Lee
  • International Conference on Neural Information Processing (ICONIP), 2017.
  • Oral | pdf

2016

[J3] Deep CNNs Along the Time Axis With Intermap Pooling for Robustness to Spectral Variations
  • Hwaran Lee, Geonmin Kim, Ho-Gyeong Kim, Sang-Hoon Oh, and Soo-Young Lee
  • IEEE Signal Processing Letters (SPL), 2016.
  • pdf | code | demo

2015

[C2] Hierarchical committee of deep CNNs with exponentially-weighted decision fusion for static facial expression recognition
  • Bo-Kyeong Kim, Hwaran Lee, Jihyeon Roh, and Soo-Young Lee
  • International Conference on Multimodal Interaction (ICMI), 2015.
  • Challenge Winner | Oral |demo
[C1] Active Learning for Large-scale Object Classification: from Exploration to Exploitation
  • Ho-Gyeong Kim, Jihyeon Roh, Hwaran Lee, Geonmin Kim, and Soo-Young Lee
  • In Proceedings of the 3rd International Conference on Human-Agent Interaction (HAI), 2015.
  • Best paper | Qualcomm Innovation Awards
[W2] Learning Tonotopically Organized Auditory Feature-map from Speech by an Intermap Pooling Layer in a Deep CNN
  • Hwaran Lee, Geonmin Kim, Jihyeon Roh, and Soo-Young Lee
  • China-Japan-Korea Joint Workshop on Neurobioloby and Neuroinformatics (NBNI), 2015. (only abstract)
  • pdf
[W1] Spoken Sentence Embedding from Character by Jointly Learning Character-level Compositional Word Model and RNN Sentence Encoder
  • Geonmin Kim, Hwaran Lee, Jaemyung Yu, and Soo-Young Lee
  • China-Japan-Korea Joint Workshop on Neurobioloby and Neuroinformatics (NBNI), 2015. (only abstract)
  • pdf

2013

[J2] A Calibration Method for Eye-Gaze Estimation Systems Based on 3D Geometrical Optics
  • Hwaran Lee, Nadeem Iqbal, Wonil Chang, and Soo-Young Lee
  • IEEE Sensors Journal (Sensors), 2013.
  • pdf
[J1] Smart User Interface for Mobile Consumer Devices Using Model-Based Eye-Gaze Estimation
  • Nadeem Iqbal, Hwaran Lee, and Soo-Young Lee
  • IEEE Transactions on Consumer Electronics (TCE), 2013.
  • pdf