5 papers
Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
Wentao Zhang, Yan Zhuang, ZhuHang Zheng +3
Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service behaviors, which are conspicuous and easy to detect…
EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue
Jiawen Deng, Wei Li, Wentao Zhang +2
Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or ethical judgment can cause…
Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts
Jiawen Deng, Wentao Zhang, Ziyun Jiao +1
Conversational AI is increasingly deployed in emotionally charged and ethically sensitive interactions. Previous research has primarily concentrated on emotional benchmarks or stat…
TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities
Yan Zhuang, Minhao Liu, Yanru Zhang +2
Multimodal Sentiment Analysis (MSA) aims to infer human sentiment by integrating information from multiple modalities such as text, audio, and video. In real-world scenarios, howev…
Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models
Zheng Hu, Zhe Li, Ziyun Jiao +5
In recent years, knowledge graphs have been integrated into recommender systems as item-side auxiliary information, enhancing recommendation accuracy. However, constructing and int…