AI Paper Atlas

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

An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement

Gaku Morio, Christopher D Manning

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: Data and evaluation methodology · 0 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
replace BERT-base with ClimateBERT (climate-domain pretraining)page-wise pipeline · Corporate climate policy engagement test (Document Q)F-score: 63.5 -> 64.0Improved
replace ClimateBERT with RoBERTa-basepage-wise pipeline · Corporate climate policy engagement test (Document Q)F-score: 64.0 -> 64.5Improved
replace RoBERTa-base with Longformer-basepage-wise pipeline · Corporate climate policy engagement test (Document S)F-score: 53.1 -> 54.6Improved
scale Longformer-base to Longformer-largepage-wise pipeline · Corporate climate policy engagement test (Strict S)F-score: 28.6 -> 31.5Improved
scale Longformer-base to Longformer-largepage-wise pipeline · Corporate climate policy engagement test (Document S)F-score: 54.6 -> 57.3Improved
train a model instead of most-frequent baselineLongformer-large · Corporate climate policy engagement test (Document P)F-score: 46.7 -> 73.9Improved
use BERT-base instead of linear tf-idf modelpage-wise pipeline · Corporate climate policy engagement test (Strict P)F-score: 52.0 -> 50.2Hurt
use BERT-base instead of linear tf-idf modelpage-wise pipeline · Corporate climate policy engagement test (Strict S)F-score: 27.0 -> 25.8Hurt
use BERT-base instead of linear tf-idf modelpage-wise pipeline · Corporate climate policy engagement test (Document Q)F-score: 61.9 -> 63.5Improved
increase number of pages per documentLongformer-large · Corporate climate policy engagement test (Strict P)F-scoreHurt
scale FlanT5-large to FlanT5-XLcomment generation · Comment generation testROUGE-1: 38.4 -> 39.5Improved
scale FlanT5-large to FlanT5-XLcomment generation · Comment generation validationROUGE-1: 43.4 -> 42.7Hurt

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