Who Spoke Next Is Not Who Should Have: What Zero-Shot Failure on Multi-Party Turn-Taking Benchmarks Measures, Why the Human Reference Sits Beside the Models, and What Would Show That Knowing When to Speak Must Be Trained

APA

Mahendrakar, P. (2026). Who Spoke Next Is Not Who Should Have: What Zero-Shot Failure on Multi-Party Turn-Taking Benchmarks Measures, Why the Human Reference Sits Beside the Models, and What Would Show That Knowing When to Speak Must Be Trained [Journal article]. Life of Research. https://doi.org/10.5281/zenodo.23396947

Copy APA

BibTeX

@misc{lor1112026,
  title        = {Who Spoke Next Is Not Who Should Have: What Zero-Shot Failure on Multi-Party Turn-Taking Benchmarks Measures, Why the Human Reference Sits Beside the Models, and What Would Show That Knowing When to Speak Must Be Trained},
  author       = {Pranay Mahendrakar},
  year         = {2026},
  publisher    = {Life of Research},
  doi          = {10.5281/zenodo.23396947},
  url          = {https://lifeofresearch.com/articles/111},
  keywords     = {turn-taking, multi-party conversation, spoken dialogue systems, large language models, operating point, human label variation, emergent abilities, benchmark validity},
  note         = {LOR-00111}
}

Copy BibTeX More on the record page