Publications

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang*, Yonghyun Jun*, Hwanhee Lee✝
ICLR 2026 [ Code/Dataset ] [ Poster ] [ Slide ]

Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusion
Jeonghyun Park, Byeongjeong Kim, Seojin Hwang, Hwanhee Lee✝
ACL 2026 (findings) [ Code ] 

MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference
Jeonghyun Park*, Ingeol Baek*, Seunghyun Yoon, Haeun Jang, Aparna Garimella, Akriti Jain, Nedim Lipka, Hwanhee Lee✝
ACL 2026 (findings) [ Code ] 

Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models
Haeun Jang*, Hwan Chang*, Hwanhee Lee✝
ACL 2026 (findings)

Personality Editing for Language Models through Adjusting Self-Referential Queries
Seojin Hwang, Yumin Kim, Byeongjeong Kim, Donghoon Shin, Hwanhee Lee✝
EACL 2026 (main) [ Poster ] [ Slide ]

MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
Weerayut Buaphet, Thanh-Nhi Nguyen, Risa Kondo, Tomoyuki Kajiwara, Yumin Kim, Jimin Lee, Hwanhee Lee, Holy Lovenia, Peerat Limkonchotiwat, Sarana Nutanong, Rob van der Goot
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)

ToDi: Token-wise Distillation via Fine-Grained Divergence Control
Seongryong Jung, Suwan Yoon, DongGeon Kim, Hwanhee Lee✝
EMNLP 2025 (main, oral, outstanding paper nominee) [ Code ]

How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
Ingeol Baek, Hwan Chang, Sunghyun Ryu, Hwanhee Lee✝
EMNLP 2025 (main, oral) [ Code ] [ Poster ] [ Slide ]

Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
Hwan Chang*, Yumin Kim*, Yonghyun Jun, Hwanhee Lee✝
EMNLP 2025 (main) [ Code/Dataset ] [ Poster ] [ Slide ]

SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL
Jimin Lee, Ingeol Baek, Byeongjeong Kim, Hyunkyung Bae, Hwanhee Lee✝
EMNLP 2025 (main)

Event-Driven Storytelling with Multiple Lifelike Humans in a 3D scene
Donggeun Lim, Jinseok Bae, Inwoo Hwang, Seungmin Lee, Hwanhee Lee, Young Min Kim
ICCV 2025

Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation
Yonghyun Jun, Hwanhee Lee✝
ACL 2025 (main) [ Code ] [ Poster ] [ Slide ]

Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification
Gyutae Park, Ingeol Baek, Byeongjeong Kim, Joongbo Shin, Hwanhee Lee✝
ACL 2025 (main) [ Code ]

Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis
Yonghyun Jun, Hwanhee Lee✝
ACL 2025 (main) [ Code ] [ Poster ] [ Slide ]

 Investigating Language Preference of Multilingual RAG Systems  
Jeonghyun Park, Hwanhee Lee✝
ACL 2025 (findings) [ Code ] [ Poster ] [ Slide ]

Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
Hwan Chang, Hwanhee Lee✝
ACL 2025 (findings) [ Poster ] [ Slide ]

AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
Minbeom Kim, Hwanhee Lee, Joonsuk Park, Hwaran Lee, Kyomin Jung
NAACL 2025 (main)

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
Ingeol Baek, Hwan Chang, Byeongjeong Kim, Jimin Lee, Hwanhee Lee✝
NAACL 2025 (findings) [ Code ] [ Poster ]

FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document
Joonho Yang, Seunghyun Yoon, Byeongjeong Kim, Hwanhee Lee✝
EMNLP 2024 (main) [ Code ] [ Slide ] [ Poster ]

IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance
Yunah Jang, Kang-il Lee, Hyunkyung Bae, Hwanhee Lee✝, Kyomin Jung✝
NAACL 2024 (main) [ Code ]

 LifeTox: Unveiling Implicit Toxicity in Life Advice
Minbeom Kim, Jahyun Koo, Hwanhee Lee, Joonsuk Park✝, Hwaran Lee, Kyomin Jung✝
NAACL 2024 (main, oral) [ Dataset ]

KoCoSa: Korean Context-aware Sarcasm Detection Dataset
Yumin Kim*, Heejae Suh*, Mingi Kim*, Dongyeon Won* and Hwanhee Lee✝
COLING 2024 [ Code/Dataset ] [ Slide ] [ Poster ]

Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions
Yerin Hwang, Yongil Kim, Hyunkyung Bae, Jeesoo Bang, Hwanhee Lee✝ and Kyomin Jung✝
COLING 2024

Asking Clarification Questions to Handle Ambiguity in Open-Domain QA
Dongryeol Lee, Segwang Kim, Minwoo Lee, Hwanhee Lee , Joonsuk Park, Sang-Woo Lee, Kyomin Jung
EMNLP 2023 (findings)  [ Code ] [ Slide ] [ Poster ]

Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources
Yerin Hwang, Yongil Kim, Hyunkyung Bae, Hwanhee Lee✝ , Jeesoo Bang, Kyomin Jung✝
EMNLP 2023 (main)

Critic-Guided Decoding for Controlled Text Generation
Minbeom Kim, Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee✝ and Kyomin Jung✝
ACL 2023 (findings) [ Code ] [ Slide ]

Task-specific Compression for Multi-task Language Models using Attribution-based Pruning
Nakyeong Yang, Yunah Jang, Hwanhee Lee, Seohyeong Jeong and Kyomin Jung
EACL 2023 (findings)

Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking
Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee✝  and Kyomin Jung✝
NAACL 2022 (findings) [ Code ] [ Slide ] [ Poster ] [ Blog ]

QACE: Asking Questions to Evaluate an Image Caption
Hwanhee Lee, Thomas Scialom, Seunghyun Yoon, Franck Dernoncourt, and Kyomin Jung
EMNLP 2021 (findings) [ Code ] [ Slide ]

CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models
Minwoo Lee, Seungpil Won, Juae Kim, Hwanhee Lee, Cheoneum Park and Kyomin Jung
CIKM 2021 [ Code ] [ Slide ]

UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, and Kyomin Jung
ACL 2021 (main) [ Code ] [ Slide ] [ Poster ]

Entangled Bidirectional Encoder to Autoregressive Decoder for Sequential Recommendation
Taegwan Kang, Hwanhee Lee, Byeongjin Choe, and Kyomin Jung
SIGIR 2021

KPQA: A Metric for Generative Question Answering Using Keyphrase Weights
Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Joongbo Shin, and Kyomin Jung
NAACL 2021 (main, oral) [ Code ] [ Slide ] [ Poster ]

Attentive Modality Hopping Mechanism for Speech Emotion Recognition
Seunghyun Yoon, Subhadeep Dey, Hwanhee Lee, Kyomin Jung
ICASSP 2020 (oral) [ Code ] [ Slide ]

Improving Neural Question Generation using Answer Separation
Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung
AAAI 2019  [ Code ]