AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Automatic Construction of Evaluation Suites for Natural Language Generation Datasets

Simon Mille, Kaustubh Dhole, Saad Mahamood, Laura Perez-Beltrachini, Varun Gangal, Mihir Kale, Emiel van Miltenburg, Sebastian Gehrmann

NeurIPS 2021 · Large language models › Language, safety and interpretability · approach: Text generation and evaluation metrics · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Evaluate on COVID-19-related news instead of the standard test distributionmT5 generation models · MLSum and XSum COVID-19 test setsBERTScore: drops of almost 40%Hurt
Test on inputs with properties unseen during trainingmT5 WebNLG models · WebNLG English and RussianperformanceHurt
Apply systematic input transformations, including back-translation, typos, punctuation removal, or component reorderingmT5 generation models · English text-to-text, dialog, and data-to-text challenge setsperformance scoresHurt
Increase the number of input propertiesmT5 Base · WebNLG EnglishBLEURT: 0.20 -> 0.08 -> 0.03 -> -0.04 -> -0.10 -> -0.10 -> -0.14Hurt
Increase input sizegeneration models · Czech Restaurants and ToTToperformanceNo clear effect
Scramble input component ordermT5 generation models · data-to-text and Schema-guided Dialoglocal recallHurt
Evaluate on inputs about female people rather than male peoplegeneration models · ToTTo people subpopulationsBLEURTHurt
Evaluate African American examples rather than the all-USA subsetgeneration models · ToTTo people subpopulationsBLEURTHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy