Papers by Xupeng Zha
LSTDial: Enhancing Dialogue Generation via Long- and Short-Term Measurement Feedback (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing dialogue systems do not utilize quality dimensions specifically designed for dialogue evaluation to guide the response generation during training. |
| Approach: | They propose a two-stage framework which generates and utilizes conversation evaluation as explicit feedback during training. |
| Outcome: | The proposed framework generates and utilizes conversation evaluation as explicit feedback during training. |
Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Knowledge-based visual reasoning (KB-VR) is a challenging task, as it requires machines not only to understand concepts and relationships of visual scenes, but also to associate them with external world knowledge to perform chain of reasoning on open-world questions. |
| Approach: | They propose a visual knowledge card (VKC) that integrates internal visual knowledge and external world knowledge produced by a knowledge generator into an image. |
| Outcome: | The proposed model achieves new state-of-the-art results compared to previous top-performing models on three popular KB-VR benchmarks. |
EmoTransKG: An Innovative Emotion Knowledge Graph to Reveal Emotion Transformation (2024.findings-acl)
Copied to clipboard
| Challenge: | EmoTransKG establishes connections and transformations between emotions across open-textual events. |
| Approach: | They propose an Emotion Knowledge Graph that establishes connections and transformations between emotions across diverse open-textual events. |
| Outcome: | The proposed model integrates with existing conversational emotion recognition models to improve the quality and effectiveness of EmoTransKG. |