Papers by Yin Jou Huang
Constructing a Culinary Interview Dialogue Corpus with Video Conferencing Tool (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing interview dialogue corpora are based on news interviews which serve the purpose of information broadcasting or entertainment. |
| Approach: | They propose an interview dialogue corpus in the culinary domain in which interviewers play an active role to elicit culinary knowledge from the cooking expert. |
| Outcome: | The proposed corpus consists of 308 interview dialogues, each about 13 minutes long, which add up to a total of 69,000 utterances. |
Is a Knowledge-based Response Engaging?: An Analysis on Knowledge-Grounded Dialogue with Information Source Annotation (2023.acl-srw)
Copied to clipboard
| Challenge: | Currently, most knowledge-grounded dialogue models focus on reflecting given external knowledge. |
| Approach: | They analyze human behavior by annotating utterances in an existing knowledge-grounded dialogue corpus and find that speaker-derived information improves dialogue engagingness. |
| Outcome: | The proposed model cannot include speaker-derived information as often as humans do. |
Improving Event Coreference Resolution by Learning Argument Compatibility from Unlabeled Data (N19-1)
Copied to clipboard
| Challenge: | Argument compatibility is a linguistic condition that is often used in event coreference resolution systems. |
| Approach: | They propose a transfer learning framework that uses unlabeled data to learn argument compatibility of event mentions. |
| Outcome: | The proposed model improves the performance of the overall event coreference model on the English dataset. |
How Personality Traits Influence Negotiation Outcomes? A Simulation based on Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Psychological evidence reveals the influence of personality traits on decision-making. |
| Approach: | They propose a simulation framework centered on large language model agents with synthesized personality traits and propose empirical insights into the strategic impacts of Big Five personality traits on outcomes of bilateral negotiations. |
| Outcome: | The proposed model can reproduce behavioral patterns observed in human negotiations. |
Extractive Summarization Considering Discourse and Coreference Relations based on Heterogeneous Graph (2021.eacl-main)
Copied to clipboard
| Challenge: | Abstractive summarization aims to select salient text spans (mostly sentences) from the input document. |
| Approach: | They propose a heterogeneous graph based model that incorporates both discourse and coreference relations between text spans of different granularity. |
| Outcome: | The proposed model is efficient and factually reliable on a benchmark summarization dataset. |
Domain Transferable Semantic Frames for Expert Interview Dialogues (2024.lrec-main)
Copied to clipboard
| Challenge: | a dataset of interview dialogues with experts in the domains of culinary and gardening domains is used to structure domain-specific knowledge in expert interviews. |
| Approach: | They analyze interview dialogues with experts in the culinary and gardening domains to understand their domain knowledge structure. |
| Outcome: | The proposed framework is effective in eliciting critical skills in domains, the authors show . they use domain-agnostic labels to identify domain-specific knowledge in interviews . |
Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Self-report questionnaires are used to assess LLM personality traits, but they fail to capture behavioral nuances due to biases and meta-knowledge contamination. |
| Approach: | They propose a multi-observer framework for personality trait assessments in LLM agents that draws on informant-report methods in psychology. |
| Outcome: | The proposed framework combines multiple observers with a subject LLM agent to assess its Big Five personality traits. |
Static and Dynamic Speaker Modeling based on Graph Neural Network for Emotion Recognition in Conversation (2022.naacl-srw)
Copied to clipboard
| Challenge: | Hence, speaker modeling is important for the task of emotion recognition in conversation (ERC). |
| Approach: | They propose a graph-based ERC model which considers conversational context and speaker personality. |
| Outcome: | The proposed model outperforms baseline and other graph-based methods on a benchmark dataset. |
How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Cognitive biases can be observed in LLMs, affecting their reliability in real-world applications. |
| Approach: | They investigate the anchoring effect in LLM-driven price negotiations . reasoning models are less prone to the anchor effect, they find . |
| Outcome: | The proposed study shows that LLMs are influenced by the anchoring effect like humans . reasoning models are less prone to the anchor effect, but personality traits are not affected . |