Jonggeun Lee

Seoul National University

Seoul, Korea

I am a Master’s student in Data Science at Seoul National University, advised by Prof. Yohan Jo. My research focuses on multi-modal foundation models, voice assistants, tool-augmented agents, and post-training & reinforcement learning.

I am particularly interested in building conversational agents that interact with the world — through tools, speech, and environments. My recent work spans adapting tool schemas to language models (ACL 2026), evaluating speaker consistency in large audio-language models (ACL 2026), and simulating spoken users for task-oriented dialogue.

Before joining SNU, I received my B.S. in Industrial Management Engineering from Korea University, graduating with Great Honors. I have also worked as an intern at Samsung Electronics (RAG for internal chatbot systems) and LG AI Research, EXAONE Lab (multi-modal pretraining data pipelines).

selected publications

ACL
Don’t Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models

Jonggeun Lee^*, Woojung Song^*, Jongwook Han, Haesung Pyun, and Yohan Jo

In Annual Meeting of the Association for Computational Linguistics (ACL). Acceptance rate: 19% , 2026

Abs Bib PDF

Proposed PA-Tool, a training-free method that adapts tool schemas to align with models’ pretrained knowledge, improving tool-use performance by up to 17% and reducing schema misalignment errors by 80%.
@inproceedings{lee2026patool, title = {Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models}, author = {Lee, Jonggeun and Song, Woojung and Han, Jongwook and Pyun, Haesung and Jo, Yohan}, booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2026}, }
ACL
SpeakerSleuth: Can LALMs Judge Speaker Consistency across Multi-turn Dialogues?

Jonggeun Lee, Junseong Pyo, Gyuhyeon Seo, and Yohan Jo

In Annual Meeting of the Association for Computational Linguistics (ACL). Acceptance rate: 19% , 2026

Abs Bib PDF

Introduced a benchmark evaluating whether Large Audio-Language Models can reliably judge speaker consistency across multi-turn conversations, revealing significant biases in prioritizing text over acoustics.
@inproceedings{lee2026speakersleuth, title = {SpeakerSleuth: Can LALMs Judge Speaker Consistency across Multi-turn Dialogues?}, author = {Lee, Jonggeun and Pyo, Junseong and Seo, Gyuhyeon and Jo, Yohan}, booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2026}, }
ICMLW
SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue

Jonggeun Lee^*, Junseong Pyo^*, Jeongmin Park, and Yohan Jo

Under review @ EMNLP 2026; Machine Learning for Audio Workshop @ ICML 2026, 2026

Abs Bib PDF

Developed a spoken user simulator that jointly generates text and speech tokens, modeling realistic spoken behaviors (cross-turn slots, barge-in, disfluency, emotion-aware speech) for task-oriented dialogue systems.
@article{lee2026spokenus, title = {SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue}, author = {Lee, Jonggeun and Pyo, Junseong and Park, Jeongmin and Jo, Yohan}, journal = {Under review @ EMNLP 2026; Machine Learning for Audio Workshop @ ICML 2026}, year = {2026}, }
ICLR
SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents

Gyuhyeon Seo, Jungwoo Yang, Junseong Pyo, Nalim Kim, Jonggeun Lee, and Yohan Jo

In International Conference on Learning Representations (ICLR). Acceptance rate (Oral): 1.13% , 2026

Oral Abs Bib PDF

Oral Presentation (acceptance rate: 1.13%)

Developed a time-accelerated smart home simulation environment with 600 benchmark episodes, revealing that even top models struggle with temporal scheduling and state verification.
@inproceedings{seo2026simuhome, title = {SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents}, author = {Seo, Gyuhyeon and Yang, Jungwoo and Pyo, Junseong and Kim, Nalim and Lee, Jonggeun and Jo, Yohan}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026}, }