Papers by Yejin Kwon
LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions (2025.acl-industry)
Copied to clipboard
| Challenge: | Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it vital for quality control and process optimization. |
| Approach: | They propose a framework that provides industrial operators with explanations for logical anomalies by compiling automatically generated questions into a checklist and collecting responses. |
| Outcome: | The proposed framework achieves state-of-the-art (SOTA) Logical AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 87.6% and an F1-max of 88.0% along with the explanations of anomalies. |
Being Kind Isn’t Always Being Safe: Diagnosing Affective Hallucination in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly engaged in emotionally vulnerable conversations that extend beyond information seeking to moments of personal distress. |
| Approach: | They propose AHaBench, a benchmark of 500 mental-health-related prompts with expert-informed reference responses, evaluated along three dimensions: Emotional Enmeshment, Illusion of Presence, and Fostering Overdependence. |
| Outcome: | The proposed model is based on 500 mental-health-related prompts with expert-informed reference responses and a 5K-instance preference dataset enabling direct preference optimization (DPO) for alignment with emotionally responsible behavior. |