Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations
Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, disfluency from conventional transcription and restructuring from AI-backed dictation tools. How do they impact an LLM's performance? In this paper we present HIVE (Human Input-Variation Engine), a suite of voice transcription perturbations and…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
