Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications
On the map: LLM safety and security → Safety alignment, refusal and guardrails
Abstract (arXiv)
Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood. In the automotive domain, this enables intuitive and humanlike in-car dialogue experiences. However, integrating these end-to-end assistants limits architectural options for programmable domain-specific safeguards. This paper discusses two implementation approaches for S2S guardrails: transcript-based and tool-based. Through an empirical evaluation, we demonstrate that both strategies are insufficient for industrial deployment in most cases due to prohibitive latency (delaying each answer by 0 to 1.4 seconds even for computationally cheap checks) and technical impediments (like potentially non-deterministic tool call behavior). Finally, we outline open challenges for S2S guardrails in the automotive context.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security. Builds on 8 of its 25 references that are in the map. First posted on arXiv 23 Jul 2026.
Builds on
8 of 25 references.
Closest ancestors · 1
Same direction, newest first
Other references · 7
- 2025Qwen2.5-Omni Technical Reportcited by 704
- 2024Moshi: a speech-text foundation model for real-time dialoguecited by 536
- 2025Kimi-Audio Technical Reportcited by 210
- 2025On The Landscape of Spoken Language Models: A Comprehensive Surveycited by 116
- 2024Recent Advances in Speech Language Models: A Surveycited by 85
- 2024A Survey on Speech Large Language Models for Understandingcited by 71
- 2025VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Modelcited by 30
Built on by
Not cited yet.