AIConfPaper
← Search

Hae Won Park

12 accepted papers

2026

Social Human Robot Embodied Conversation (SHREC) Dataset: Benchmarking Foundational Models’ Social Reasoning

Dong Won Lee, Yubin Kim, Sooyeon Jeong, Denison Guvenoz, Parker Malachowsky, Louis-Philippe Morency +2
RSS 2026poster

Our work focuses on the social reasoning capabilities of foundational models for real-world human–robot interactions. We introduce the Social Human Robot Embodied Conversation (SHREC) Dataset, a large-scale benchmark of 400 real-world human-robot interaction videos and over 10K annotations, capturin…

Cited by 0Source ↗Scholar ↗
2025

Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition

Dong Won Lee, Hae Won Park, Cynthia Breazeal, Louis-Philippe Morency
EMNLP 2025

We propose a large language model based reward decomposition framework for aligning dialogue agents using only a single session-level feedback signal. We leverage the reasoning capabilities of a frozen, pretrained large language model (LLM) to infer fine-grained local implicit rewards by decomposing

Cited by 0Source ↗PDF ↗Scholar ↗
2025

BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum

Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park +8
EMNLP 2025

Large Language Models (LLMs) as agents require careful behavioral adaptation. While adept at reactive tasks (e.g., medical reasoning), LLMs often struggle with proactive engagement, like unprompted identification of critical missing information or risks. We introduce **BehaviorBench**, a comprehensi

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication

Jocelyn J Shen, Akhila Yerukola, Xuhui Zhou, Cynthia Breazeal, Maarten Sap, Hae Won Park
EMNLP 2025

Conversational breakdowns in close relationships are deeply shaped by personal histories and emotional context, yet most NLP research treats conflict detection as a general task, overlooking the relational dynamics that influence how messages are perceived. In this work, we leverage nonviolent commu

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Global Reward to Local Rewards: Multimodal-Guided Decomposition for Improving Dialogue Agents

Dong Won Lee, Hae Won Park, Yoon Kim, Cynthia Breazeal, Louis-Philippe Morency
EMNLP 2024main

We describe an approach for aligning an LLM based dialogue agent for long-term social dialogue, where there is only a single global score given by the user at the end of the session. In this paper, we propose the usage of denser naturally-occurring multimodal communicative signals as local implicit…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs

Jocelyn Shen, Joel Mire, Hae Won Park, Cynthia Breazeal, Maarten Sap
EMNLP 2024main

Empathy serves as a cornerstone in enabling prosocial behaviors, and can be evoked through sharing of personal experiences in stories. While empathy is influenced by narrative content, intuitively, people respond to the way a story is told as well, through narrative style. Yet the relationship betwe…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making

Yubin Kim, Chanwoo Park, Hyewon Jeong, Yik Siu Chan, Xuhai Xu, Daniel McDuff +4
NeurIPS 2024oral

Foundation models are becoming valuable tools in medicine. Yet despite their promise, the best way to leverage Large Language Models (LLMs) in complex medical tasks remains an open question. We introduce a novel multi-agent framework, named **M**edical **D**ecision-making **Agents** (**MDAgents**) t…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗
2023

Modeling Empathic Similarity in Personal Narratives

Jocelyn J Shen, Maarten Sap, Pedro Colon-Hernandez, Hae Won Park, Cynthia Breazeal
EMNLP 2023long main

The most meaningful connections between people are often fostered through expression of shared vulnerability and emotional experiences in personal narratives. We introduce a new task of identifying similarity in personal stories based on empathic resonance, i.e., the extent to which two people empat…

Cited by 0Source ↗Scholar ↗
2023

MultiPar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations

Dong Won Lee, Yubin Kim, Rosalind W. Picard, Cynthia Breazeal, Hae Won Park
IJCAI 2023poster

As we move closer to real-world social AI systems, AI agents must be able to deal with multiparty (group) conversations. Recognizing and interpreting multiparty behaviors is challenging, as the system must recognize individual behavioral cues, deal with the complexity of multiple streams of data fro…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2021

MRF-Chat: Improving Dialogue with Markov Random Fields

Ishaan Grover, Matthew Huggins, Cynthia Breazeal, Hae Won Park
EMNLP 2021main

Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph and persona of the agent and the user, among others.…

Cited by 1Source ↗PDF ↗Scholar ↗
2017

Backchannel opportunity prediction for social robot listeners

Hae Won Park, Mirko Gelsomini, Jin Joo Lee, Tonghui Zhu, Cynthia Breazeal
ICRA 2017poster

This paper investigates how a robot that can produce contingent listener response, i.e., backchannel, can deeply engage children as a storyteller. We propose a backchannel opportunity prediction (BOP) model trained from a dataset of children's dyad storytelling and listening activities. Using this d…

Cited by 28Source ↗Scholar ↗
2015

Retrieving experience: Interactive instance-based learning methods for building robot companions

Hae Won Park, Ayanna M. Howard
ICRA 2015poster

A robot companion should adapt to its user's needs by learning to perform new tasks. In this paper, we present a robot playmate that learns and adapts to tasks chosen by the child on a touchscreen tablet. We aim to solve the task learning problem using an experience-based learning framework that sto…

Cited by 16Source ↗Scholar ↗