collaborators

6 papers

cs.LG2025

PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis

Kang He, Boyu Chen, Yuzhe Ding +3

Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cros…

cs.CL2025

DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning

Kang He, Yuzhe Ding, Haining Wang +3

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, fac…

cs.CL2025

Zero-Shot Conversational Stance Detection: Dataset and Approaches

Yuzhe Ding, Kang He, Bobo Li +5

Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the increasing number of online…

cs.CL2025

Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge

Li Zheng, Sihang Wang, Hao Fei +5

Text-based hyperbole and metaphor detection are of great significance for natural language processing (NLP) tasks. However, due to their semantic obscurity and expressive diversity…

cs.CL2025

DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement

Shaoqing Lin, Chong Teng, Fei Li +3

Vision-Language Models (VLMs) generate discourse-level, multi-sentence visual descriptions, challenging text scene graph parsers built for single-sentence caption-to-graph mapping.…

cs.AI2025

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions

Xiaorui Wu, Fei Li, Xiaofeng Mao +6

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservat…