Papers by Cynthia Breazeal
MRF-Chat: Improving Dialogue with Markov Random Fields (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to deep learning for open-domain dialogue include training end-to-end models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts and persona of the agent and the user, among others. |
| Approach: | They propose a probabilistic approach using Markov Random Fields to augment existing deep-learning methods for improved next utterance prediction. |
| Outcome: | The proposed approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents. |
HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Empathy is a foundational psychological process that drives many prosocial functions. |
| Approach: | They propose a theory-based taxonomy that delineates elements of narrative style that can lead to empathy with the narrator of a story. |
| Outcome: | The proposed taxonomy delineates elements of narrative style that can lead to empathy with the narrator of a story. |
Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication (2025.emnlp-main)
Copied to clipboard
| Challenge: | a recent study examines the role of personalization in enabling LLMs to serve as effective mediators in human communication for authentic connection. |
| Approach: | They leverage nonviolent communication theory to evaluate LLMs in detecting conversational breakdowns . they annotate a subset of dialogues and obtain fine-grained labels of communication breakdown types . |
| Outcome: | The proposed dataset analyzes human interactions and relationships in a human context. |
RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations (2021.findings-acl)
Copied to clipboard
| Challenge: | Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). |
| Approach: | They propose a system that uses two GANs to learn a one-to-one mapping between concepts and retrofitted counterparts. |
| Outcome: | The proposed system performs well on word-similarity benchmarks and a sentence simplification task. |
BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum (2025.findings-emnlp)
Copied to clipboard
Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park
| Challenge: | Large Language Models (LLMs) struggle with proactive engagement, authors say . a blind clinical evaluation confirmed that trained agents exhibit more realistic clinical behavior . |
| Approach: | They propose a training strategy using behavioral tokens to explicitly condition LLMs for dynamic behavioral selection. |
| Outcome: | The proposed training strategy boosts performance on both benchmarks. |
Global Reward to Local Rewards: Multimodal-Guided Decomposition for Improving Dialogue Agents (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for asynchronous dialogue agents only use a single global score at the end of the session. |
| Approach: | They propose a method for aligning an LLM-based dialogue agent for long-term social dialogue . they use local implicit feedback to decompose a human-provided global Explicit reward . |
| Outcome: | The proposed approach improves the turn-level utterance generation across conversational metrics compared to baseline methods. |
Modeling Empathic Similarity in Personal Narratives (2023.emnlp-main)
Copied to clipboard
| Challenge: | EmpathicStories is a dataset of 1,500 personal stories annotated with empathic similarity features and 2,000 pairs of stories annnotated by empathism. |
| Approach: | They propose a task to identify similarity in personal stories based on empathic resonance . they use a dataset of 1,500 personal stories annotated with empathism features . |
| Outcome: | The proposed model outperforms semantic similarity models on correlation and retrieval metrics. |
Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a large language model is used to decompose global feedback into a lightweight reward model. |
| Approach: | They propose a large language model based reward decomposition framework for dialogue agents . they use a frozen large language modeling framework to decompose global feedback . |
| Outcome: | The proposed framework infers fine-grained local rewards from a single session-level feedback signal. |
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs (2026.findings-acl)
Copied to clipboard
Zhiyuan Hu, Yucheng Wang, Yufei He, Jiaying Wu, Yilun Zhao, See-Kiong Ng, Cynthia Breazeal, Anh Tuan Luu, Hae Won Park, Bryan Hooi
| Challenge: | Reinforcement learning (RL) is a paradigm for post-training large language models, but it suffers from exploration collapse . a new study finds that RL fails to reward correct solutions that exhibit rare high-level strategies . |
| Approach: | They propose a method that rewards correct solutions that exhibit rare high-level strategies by clustering rollouts according to their high- level solution strategies. |
| Outcome: | The proposed approach improves pass@k across large sampling budgets and increases area under the pass@K curve (AUC@K) without sacrificing pass@1. |
EmpathicStories++: A Multimodal Dataset for Empathy Towards Personal Experiences (2024.findings-acl)
Copied to clipboard
Jocelyn Shen, Yubin Kim, Mohit Hulse, Wazeer Zulfikar, Sharifa Alghowinem, Cynthia Breazeal, Hae Park
| Challenge: | Existing datasets for empathy modeling are limited in the ways they are not captured in the wild. |
| Approach: | They propose a multimodal dataset for empathy during personal experience sharing that contains 53 hours of video, audio, and text data of 41 participants. |
| Outcome: | The EmpathicStories++ dataset contains 53 hours of video, audio, and text data of 41 participants sharing vulnerable experiences and reading empathically resonant stories with an AI agent. |
PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits (2024.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that LLMs can generate content that aligns with their assigned personality traits, but there is limited research on whether they consistently reflect specific personality traits. |
| Approach: | They propose to study the behavior of LLM-based agents which they refer to as LLM personas and simulate them to measure their personality traits. |
| Outcome: | The proposed model is based on the Big Five personality model and has been validated by human evaluations and automatic evaluations. |