keyword

academic benchmarking

Academic benchmarking is the standardized evaluation and comparative assessment of computational models, algorithms, or systems using uniform datasets, quantitative metrics, and experimental protocols. In scientific and computational research, this practice establishes transparent, reproducible baselines that enable researchers to track technological progress, identify systematic limitations, and fairly contrast the relative performance of differing methodologies. By providing shared reference standards across the research community, academic benchmarking ensures that performance claims and scientific discoveries can be independently validated, compared, and consistently tracked over time.

1 item

On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research

Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker

OrganizationsCohereRecod.aiSchool of Electrical and Computer EngineeringUniversity of Campinas

Why you should read this

Reveals how unannounced updates to commercial toxicity evaluation APIs like Perspective alter benchmark leaderboards and invalidate prior research conclusions, while establishing concrete guidelines to ensure reproducible evaluations over time.

Perception of toxicity evolves over time and often differs between geographies and cultural backgrounds. Similarly, black-box commercially available APIs for detecting toxicity, such as the Perspective API, are not static, but frequently retrained to address any unattended weaknesses and biases. We evaluate the implications of these changes on the reproducibility of findings that compare the relative merits of models and methods that aim to curb toxicity. Our findings suggest that research that relied on inherited automatic toxicity scores to compare models and techniques may have resulted in inaccurate findings. Rescoring all models from HELM, a widely respected living benchmark, for toxicity with the recent version of the API led to a different ranking of widely used foundation models. We suggest caution in applying apples-to-apples comparisons between studies and lay recommendations for a more structured approach to evaluating toxicity over time. 1

Source

https://aclanthology.org/2023.emnlp-main.472.pdf

Added

2026-09-26