most citedLessons from the Trenches on Reproducible Evaluation of Language Models

5 citations · 5 across the 1 of their papers we have counts for

collaborators

7 papers

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.LG2025

Eliciting Latent Predictions from Transformers with the Tuned Lens

Nora Belrose, Igor Ostrovsky, Lev McKinney +5

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for…

cs.CL2025

Explaining and Mitigating Crosslingual Tokenizer Inequities

Catherine Arnett, Tyler A. Chang, Stella Biderman +1

The number of tokens it takes to encode parallel text in different languages is known to vary. These disparities are called token premiums. Having high token premiums leads to less…

cs.CL2025

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

Guijin Son, Jiwoo Hong, Honglu Fan +8

Recent advances in large language models (LLMs) have fueled the vision of automated scientific discovery, often called AI Co-Scientists. To date, prior work casts these systems as…

cs.CL2025

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Oskar van der Wal, Pietro Lesci, Max Muller-Eberstein +4

The stability of language model pre-training and its effects on downstream performance are still understudied. Prior work shows that the training process can yield significantly di…

cs.LG2025

LEACE: Perfect linear concept erasure in closed form

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel +3

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. rem…