NLP

Evaluation Examples Are Not Equally Informative: How Should That Change NLP Leaderboards?

August 1, 2021

Abstract

Leaderboards are widely used in NLP and push the field forward. While leaderboards are a straightforward ranking of NLP models, this simplicity can mask nuances in evaluation items (examples) and subjects (NLP models). Rather than replace leaderboards, we advocate a re-imagining so that they better highlight if and where progress is made. Building on educational testing, we create a Bayesian leaderboard model where latent subject skill and latent item difficulty predict correct responses. Using this model, we analyze the ranking reliability of leaderboards. Afterwards, we show the model can guide what to annotate, identify annotation errors, detect overfitting, and identify informative examples. We conclude with recommendations for future benchmark tasks.

Download the Paper

AUTHORS

Written by

Pedro Rodriguez

Joe Barrow

Alexander Hoyle

John P. Lalor

Robin Jia

Jordan Boyd-Graber

Publisher

ACL

Research Topics

Natural Language Processing

Related Publications

November 16, 2022

NLP

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Kushal Tirumala, Aram H. Markosyan, Armen Aghajanyan, Luke Zettlemoyer

November 16, 2022

October 31, 2022

NLP

Autoregressive Search Engines: Generating Substrings as Document Identifiers

Fabio Petroni, Giuseppe Ottaviano, Michele Bevilacqua, Patrick Lewis, Scott Yih, Sebastian Riedel

October 31, 2022

December 06, 2020

NLP

Pre-training via Paraphrasing

Michael Lewis, Armen Aghajanyan, Gargi Ghosh, Luke Zettlemoyer, Marjan Ghazvininejad, Sida Wang

December 06, 2020

November 30, 2020

NLP

Where Are You? Localization from Embodied Dialog

Dhruv Batra, Devi Parikh, Meera Hahn, Jacob Krantz, James Rehg, Peter Anderson, Stefan Lee

November 30, 2020

April 30, 2018

NLP

Speech & Audio

Identifying Analogies Across Domains | Facebook AI Research

Yedid Hoshen, Lior Wolf

April 30, 2018

November 01, 2018

NLP

Computer Vision

Non-Adversarial Unsupervised Word Translation | Facebook AI Research

Yedid Hoshen, Lior Wolf

November 01, 2018

December 02, 2018

NLP

Computer Vision

One-Shot Unsupervised Cross Domain Translation | Facebook AI Research

Sagie Benaim, Lior Wolf

December 02, 2018

June 30, 2019

NLP

Variational Training for Large-Scale Noisy-OR Bayesian Networks | Facebook AI Research

Geng Ji, Dehua Cheng, Huazhong Ning, Changhe Yuan, Hanning Zhou, Liang Xiong, Erik B. Sudderth

June 30, 2019

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.