- Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
Siyuan Liu, Jiahui Xu, Feng Jiang, Kuang Wang, Zefeng Zhao · Feb 26, 2026
Automatic Metrics General
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems.
- Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment
Sanjid Hasan, Risalat Labib, A H M Fuad, Bayazid Hasan · Feb 26, 2026
Automatic Metrics General
Ultimately, this work outlines a highly optimized dual pipeline achieving a $\sim$0.019 Real-Time Factor (RTF), establishing a practical, empirically backed benchmark for low-resource, long-form speech processing.
- Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing
An-Ci Peng, Kuan-Tang Huang, Tien-Hong Lo, Hung-Shin Lee, Hsin-Min Wang · Feb 26, 2026
Automatic Metrics General
Taiwanese Hakka is a low-resource, endangered language that poses significant challenges for automatic speech recognition (ASR), including high dialectal variability and the presence of two distinct writing systems (Hanzi and Pinyin).
- Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG
Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni · Feb 24, 2026
Automatic Metrics General
Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.
- Training-Free Intelligibility-Guided Observation Addition for Noisy ASR
Haoyang Li, Changsong Liu, Wei Rao, Hao Shi, Sakriani Sakti · Feb 24, 2026
Simulation Env General
Automatic speech recognition (ASR) degrades severely in noisy environments.
- AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
Che Wang, Jiaming Zhang, Ziqi Zhang, Zijie Wang, Yinghui Wang · Feb 24, 2026
Simulation Env General
The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution.
- ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
Che Wang, Fuyao Zhang, Jiaming Zhang, Ziqi Zhang, Yinghui Wang · Feb 24, 2026
Automatic Metrics General
Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution.
- MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav, Ava Cai, Kevin Zhu · Feb 21, 2026
Automatic Metrics General
Defending LLMs against adversarial jailbreak attacks remains an open challenge.
- ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models
Zefang Liu, Chenyang Zhu, Sangwoo Cho, Shi-Xiong Zhang · Feb 21, 2026
Automatic Metrics General
Experimental results across diverse benchmarks demonstrate that ReHear effectively mitigates error propagation, consistently outperforming both supervised and pseudo-labeling baselines.
- The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?
Jayadev Billa · Feb 19, 2026
Automatic Metrics General
Current speech LLMs largely perform implicit ASR: on tasks solvable from a transcript, they are behaviorally and mechanistically equivalent to simple Whisper$\to$LLM cascades.
- Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
Jyotin Goel, Souvik Maji, Pratik Mazumder · Feb 19, 2026
Automatic Metrics General
Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates.
- What Matters For Safety Alignment?
Xing Li, Hui-Ling Zhen, Lihao Yin, Xianzhi Yu, Zhenhua Dong · Jan 7, 2026
Automatic Metrics General
This paper presents a comprehensive empirical study on the safety alignment capabilities.
- Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, Faeze Brahman, Sachin Kumar · Oct 30, 2025
Automatic Metrics General
Our finetuned models achieve consistent improvements on instruction following and instruction hierarchy benchmarks, achieving roughly a 20% improvement on the IHEval conflict setup.
- When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
Yuxin Xiao, Sana Tonekaboni, Walter Gerych, Vinith Suriyakumar, Marzyeh Ghassemi · Jun 9, 2025
Automatic Metrics General
In this work, we seek to understand whether style patterns compromise LLM safety, how superficial style alignment increases model vulnerability, and how best to mitigate these risks during alignment.
- RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Zeyi Liao, Jaylen Jones, Linxi Jiang, Yuting Ning, Eric Fosler-Lussier · May 28, 2025
Simulation Env General
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection.
