A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench

Schlangen, David and Hakimov, Sherzod and Kranti, Chalamalasetti and Jordan, Jonathan and Sadler, Philipp

, 2026
[PDF]
@misc{Schlangen-2025,
  title = {A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench},
  author = {Schlangen, David and Hakimov, Sherzod and Kranti, Chalamalasetti and Jordan, Jonathan and Sadler, Philipp},
  year = {2026},
  eprint = {2507.08491},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url = {https://arxiv.org/abs/2507.08491}
}