AI Paper Atlas

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

Abductive Commonsense Reasoning

Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen-tau Yih, Yejin Choi

ICLR 2020 · Large language models › Language, safety and interpretability · approach: Data and evaluation methodology · 33 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
Jointly model both observations rather than impose linear-chain independence (ablation)BERT for alphaNLI · ART testaccuracy: 68.9 (0.5) -> 68.6 (0.5)No clear effect
Restrict input to the second observation and hypothesis instead of using the linear-chain model (ablation)BERT for alphaNLI · ART testaccuracy: 68.9 (0.5) -> 66.6 (0.2)Hurt
Restrict input to the first observation and hypothesis instead of using the linear-chain model (ablation)BERT for alphaNLI · ART testaccuracy: 68.9 (0.5) -> 63.5 (0.7)Hurt
Use only the hypothesis instead of the linear-chain model (ablation)BERT for alphaNLI · ART testaccuracy: 68.9 (0.5) -> 59.5 (0.2)Hurt
Add COMeT embeddings to GPT2 conditioned on both observations (ablation)GPT2 alphaNLG · ART testBLEU: 2.23 -> 3.03Improved
Add COMeT embeddings to GPT2 conditioned on both observations (ablation)GPT2 alphaNLG · ART testHuman evaluation: 42.26 -> 44.56Improved
Provide COMeT in text form rather than as embeddings (ablation)GPT2 alphaNLG · ART testBLEU: 2.23 -> 2.29No clear effect
Pre-train on ART before fine-tuning on WinoGrande (ablation)BERT · WinoGrandeaccuracy: 65.8% -> 67.2%Improved
Pre-train on ART before fine-tuning on WSC (ablation)BERT · WSCaccuracy: 70.0% -> 74.0%Improved
Pre-train on ART before fine-tuning on DPR (ablation)BERT · DPRaccuracy: 72.5% -> 86.0%Improved
Pre-train on ART before fine-tuning on HellaSwag (ablation)BERT · HellaSwagaccuracy: 46.7% -> 46.1%Hurt

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