most citedLessons from the Trenches on Reproducible Evaluation of Language Models

5 citations · 6 across the 4 of their papers we have counts for

collaborators

5 papers

cs.AI2026

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Mubashara Akhtar, Anka Reuel, Prajna Soni +36

Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult…

cs.AI2026

Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving

Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman

Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof. However, the kerne…

cs.CL20265 cited

Lessons from the Trenches on Reproducible Evaluation of Language Models

Stella Biderman, Hailey Schoelkopf, Lintang Sutawika +27

Reliable evaluation of language models (LMs) remains an open challenge. Re- searchers and engineers face methodological issues such as the sensitivity of models to evaluation setup…

cs.CY20261 cited

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

Anka Reuel, Avijit Ghosh, Jenny Chim +32

Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general c…

cs.LG2024

Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models

Alex Havrilla, Andrew Dai, Laura O'Mahony +17

Synthetic data generation with Large Language Models is a promising paradigm for augmenting natural data over a nearly infinite range of tasks. Given this variety, direct compariso…