Research map / Large language models / Language, safety and interpretability
Don’t Pass@$k$: A Bayesian Framework for Large Language Model Evaluation
Mohsen Hariri, Amirhossein Samandar, Michael Hinczewski, Vipin Chaudhary
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Bayes@N instead of Pass@k, Pass^k, G-Pass@k, mG-Pass@k | LLM ranking · biased-coin simulation (11 mimics) | Kendall tau vs true ranking | Improved |
| use Bayes@N instead of Pass@k variants | LLM ranking · HMMT'25 (11 LLMs) | mean convergence@n trials: 69.5 -> 44.2 | Improved |
| use Bayes@N instead of Pass@k variants | LLM ranking · BrUMO'25 (11 LLMs) | mean convergence@n trials: 48.5 -> 27.1 | Improved |
| use Bayes@N instead of Pass@k variants | LLM ranking · AIME'25 (11 LLMs) | convergence within 80 trials | Mixed |
| add non-uniform prior from D=1 to 4 trials of original model (ablation) | Bayes@N · synthetic updated-model rankings | Kendall tau at small N | Improved |
| use large prior weight D=8 or 16 (ablation) | Bayes@N · synthetic updated-model rankings | Kendall tau at larger N | Hurt |
| add 95% credible interval to ranking (ablation) | Bayes@80 · AIME'25, AIME'24, HMMT'25, BrUMO'25 | rank resolution | Mixed |
| increase number of models ranked to 20 (ablation) | Avg@N and Pass@k family · four math datasets | ranking convergence | Hurt |
Closest papers by meaning
- An Empirical Analysis of Uncertainty in Large Language Model Evaluations (ICLR 2025 · similarity 0.92)
- RocketEval: Efficient automated LLM evaluation via grading checklist (ICLR 2025 · similarity 0.90)
- Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints (ICML 2025 · similarity 0.90)
- Benchmarking LLMs via Uncertainty Quantification (NeurIPS 2024 · similarity 0.90)
- Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation (NeurIPS 2025 · similarity 0.90)
- Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals (ICML 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
