Efficient Distillation of Multi-task Speech Models via Language-Specific Experts

2025-12-03

[Submitted on 2 Nov 2023 (v1), last revised 29 Nov 2025 (this version, v4)] View a PDF of the paper ...

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons

2025-12-02

arXiv:2512.01797v1 Announce Type: cross Abstract: Large language models (LLMs) frequently generate hallucinations — plausible but factually incorrect outputs — undermining ...

SO-Bench: A Structural Output Evaluation of Multimodal LLMs

2025-12-01

arXiv:2511.21750v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly deployed in real-world, agentic settings where outputs must ...

An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning

2025-12-01

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals ...

[2510.21984] AI-Mediated Communication Reshapes Social Structure in Opinion-Diverse Groups

2025-11-28

[Submitted on 24 Oct 2025 (v1), last revised 25 Nov 2025 (this version, v2)] View a PDF of the paper ...

A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation

2025-11-27

[Submitted on 24 May 2025 (v1), last revised 25 Nov 2025 (this version, v2)] View a PDF of the paper ...

[2410.13334] BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models

2025-11-26

[Submitted on 17 Oct 2024 (v1), last revised 25 Nov 2025 (this version, v5)] View a PDF of the paper ...

An AI Pipeline For Real-time Disease Outbreak Detection

2025-11-26

[Submitted on 24 Jun 2025 (v1), last revised 24 Nov 2025 (this version, v2)] Authors:Devesh Pant, Rishi Raj Grandhe, Vipin ...

PRInTS: Reward Modeling for Long-Horizon Information Seeking

2025-11-25

arXiv:2511.19314v1 Announce Type: cross Abstract: Information-seeking is a core capability for AI agents, requiring them to gather and reason over ...