Papers by Sungzoon Cho
EXPERT: An Explainable Image Captioning Evaluation Metric with Structured Explanations (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on explainable evaluation metrics generate explanations without standardized criteria and the overall quality of the generated explanations remains unverified. |
| Approach: | They propose a reference-free evaluation metric that provides structured explanations based on fluency, relevance, and descriptiveness. |
| Outcome: | The proposed evaluation template achieves state-of-the-art on benchmark datasets while providing significantly higher-quality explanations than existing metrics. |
KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapy (2025.naacl-long)
Copied to clipboard
| Challenge: | Motivational Interviewing (MI) is gaining attention as a theoretical basis for mental health chatbots. |
| Approach: | They propose a framework that simulates MI sessions enriched with the expertise of professional therapists by using large language models to generate utterances through prompt engineering. |
| Outcome: | The proposed framework simulates MI sessions enriched with the expertise of professional therapists and employs large language models to generate utterances through prompt engineering. |
PsyProbe: Proactive and Interpretable Dialogue through User State Modeling for Exploratory Counseling (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to mental health dialogue are reactive and lack systematic user state modeling for proactive therapeutic exploration. |
| Approach: | They propose a dialogue system designed for the exploration phase of counseling that systematically tracks user psychological states through the PPPPPI framework augmented with cognitive error detection. |
| Outcome: | The proposed system outperforms baseline and ablation modes in automatic evaluation and expert evaluation by a certified counselor. |
SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences (2026.findings-acl)
Copied to clipboard
| Challenge: | Speculative decoding performance degrades as input length increases, with significant drops even at moderate lengths. |
| Approach: | They propose a drop-in enhancement that improves speculative decoding on long sequences without additional training. |
| Outcome: | The proposed enhancement accelerates speculative decoding by up to 2.84 on 16K-token long document summarization and up to 3.86 on long-form reasoning while preserving the short-input performance of state-of-the-art frameworks. |
LLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in Dialogue (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating user satisfaction with dialogue systems face challenges due to limited understanding of underlying reasons for user dissatisfaction and high costs of annotating user intentions. |
| Approach: | They propose an interpretable framework for effective user satisfaction prediction . they propose to align utterances with strategies and large language models to retrieve relevant features from utterations. |
| Outcome: | The proposed framework achieves state-of-the-art performance on three benchmarks for the USE task. |
Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models place excessive reasoning burden on response generation, causing performance degradation . we present a new approach that shifts complex reasoning processes from inference to memory construction . |
| Approach: | a new approach shifts complex reasoning processes from inference to memory construction . PREMem extracts fine-grained memory fragments and establishes explicit relationships . small models achieve comparable results even with limited token budgets . |
| Outcome: | The proposed approach reduces the computational burden of response generation by capturing evolution patterns in memory items. |