5 papers
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
Yuanhe Zhao, Tianyu Zhang, Huafei Xing +3
Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious promp…
Segment-Level Mandarin Chinese Speech-Based Cognitive Impairment Detection via an Autoencoder with Contrastive Learning
Yongqi Shao, Hong Huo, Flavio Bertini +2
\noindent\textbf{Background and Objective:} Speech has emerged as a low-cost and non-invasive digital biomarker with considerable potential for cognitive impairment detection. Howe…
From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models
Jiaxu Zuo, Mu You, Kaixin Lan +5
Recent advances in Large Language Models (LLMs) have substantially transformed Automated Essay Scoring (AES), yet the internal mechanisms underlying LLM-based scoring remain poorly…
Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge
Wentao Zhang, Qi Zhang, Mingkun Xu +6
Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names, and when predictions are corr…
Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization
Keyan Jin, Yapeng Wang, Leonel Santos +4
Dialogue summarization is a challenging task with significant practical value in customer service, meeting analysis, and conversational AI. Although large language models (LLMs) ha…