AI model builders mostly highlight unique benchmarks that act as flexible narrative tools for market positioning rather than standardized scientific measurements.
arXiv preprint arXiv:2112.01716 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing concentration on fewer and fewer datasets within task communities, significant adoption of datasets from other tasks, and concentration across the field on datasets that have been introduced by researchers situated within a small number of elite institutions. Our results have implications for scientific evaluation, AI ethics, and equity/access within the field.
representative citing papers
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.
A scoping review organizes decades of NLP evaluation debates into a taxonomy of recurring concerns and trade-offs with a structured checklist for better evaluation design.
citing papers explorer
-
Unsteady Metrics and Benchmarking Cultures of AI Model Builders
AI model builders mostly highlight unique benchmarks that act as flexible narrative tools for market positioning rather than standardized scientific measurements.
-
Validating Causal Abstraction Metrics on Simulated Complex Systems
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
-
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
-
Rethinking Indic AI from a Lens of Cultural Heritage Preservation
The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.
-
Evaluation Revisited: A Taxonomy of Evaluation Concerns in Natural Language Processing
A scoping review organizes decades of NLP evaluation debates into a taxonomy of recurring concerns and trade-offs with a structured checklist for better evaluation design.