Nima Yazdani

Rumi Allbert, Nima Yazdani, Ali Ansari et al. · stanford

Voice-based conversational AI systems increasingly rely on cascaded architectures that combine speech-to-text (STT), large language models (LLMs), and text-to-speech (TTS) components. We present a large-scale empirical comparison of STT x LLM x TTS stacks using data sampled from over 300,000 AI-conducted job interviews. We used an LLM-as-a-Judge automated evaluation framework to assess conversational quality, technical accuracy, and skill assessment capabilities. Our analysis of five production configurations reveals that a stack combining Google's STT, GPT-4.1, and Cartesia's TTS outperforms alternatives in both objective quality metrics and user satisfaction scores. Surprisingly, we find that objective quality metrics correlate weakly with user satisfaction scores, suggesting that user experience in voice-based AI systems depends on factors beyond technical performance. Our findings provide practical guidance for selecting components in multimodal conversations and contribute a validated evaluation methodology for human-AI interactions.

Ada Aka, Emil Palikot, Ali Ansari et al.

Artificial intelligence (AI) is increasingly used in recruitment, yet empirical evidence quantifying its impact on hiring efficiency and candidate selection remains limited. We randomly assign 37,000 applicants for a junior-developer position to either a traditional recruitment process (resume screening followed by human selection) or an AI-assisted recruitment pipeline incorporating an initial AI-driven structured video interview before human evaluation. Candidates advancing from either track faced the same final-stage human interview, with interviewers blind to the earlier selection method. In the AI-assisted pipeline, 54% of candidates passed the final interview compared with 34% from the traditional pipeline, yielding an average treatment effect of 20 percentage points (SE 12 pp.). Five months later, we collected LinkedIn profiles of top applicants from both groups and found that 18% (SE 1.1%) of applicants from the traditional track found new jobs compared with 23% (SE 2.3%) from the AI group, resulting in a 5.9 pp. (SE 2.6 pp.) difference in the probability of finding new employment between groups. The AI system tended to select younger applicants with less experience and fewer advanced credentials. We analyze AI-generated interview transcripts to examine the selection criteria and conversational dynamics. Our findings contribute to understanding how AI technologies affect decision making in recruitment and talent acquisition while highlighting some of their potential implications.