Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations

In 30 Sekunden

Was passiert ist

Researchers tested how voice and keyboard input errors affect LLM performance, finding voice transcription errors hurt accuracy more than typing mistakes.

Warum es zählt

Matters for engineers building voice interfaces, chatbots, or agents where users input commands through speech or text.

Achtung

The study shows thinking time helps keyboard input but not voice, and lightweight model adaptation cannot fix the voice robustness gap.