AI Paper Atlas

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

What if We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks

Haohan Wang, Da Sun, Eric P. Xing

AAAI 2019 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations

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
Swap premise and hypothesis at test timeCBOW, InferSent, DGA, ESIM, KIM, and ADV · NLI Test, entailment pairsaccuracy: 0.856 -> 0.080 (CBOW); 0.880 -> 0.087 (InferSent); 0.854 -> 0.422 (DGA); 0.884 -> 0.324 (ESIM); 0.895 -> 0.095 (KIM); 0.Hurt
Swap premise and hypothesis at test timeCBOW, InferSent, DGA, ESIM, KIM, and ADV · NLI Test, contradiction pairsaccuracy: 0.740 -> 0.580 (CBOW); 0.859 -> 0.682 (InferSent); 0.711 -> 0.650 (DGA); 0.861 -> 0.701 (ESIM); 0.845 -> 0.796 (KIM); 0.Hurt
Swap premise and hypothesis at test timeCBOW, InferSent, DGA, ESIM, KIM, and ADV · NLI Test, neutral pairsaccuracy: 0.659 -> 0.589 (CBOW); 0.795 -> 0.712 (InferSent); 0.700 -> 0.619 (DGA); 0.801 -> 0.720 (ESIM); 0.781 -> 0.675 (KIM); 0.Hurt
Train with some neutral and contradiction pairs swapped (ablation)InferSent · Stress Test Antonymyaccuracy: 22.87 -> 27.61 (matched); 16.92 -> 21.57 (mismatched)Improved
Train with some neutral and contradiction pairs swapped (ablation)ESIM · Stress Test Word Overlapaccuracy: 57.41 -> 37.73 (matched); 58.27 -> 37.52 (mismatched)Hurt
Train with some neutral and contradiction pairs swapped (ablation)ESIM · Stress Test Spelling Erroraccuracy: 57.09 -> 37.40 (matched); 56.48 -> 37.54 (mismatched)Hurt
Train with some neutral and contradiction pairs swapped (ablation)ADV · Stress Test Antonymyaccuracy: 33.63 -> 20.69 (matched); 30.22 -> 20.88 (mismatched)Hurt
Train with some neutral and contradiction pairs swapped (ablation)DGA · Stress Testdeviation: Devi 0.073 for Antonymy; 0.009 for Length Mismatch; 0.025 for Negation; 0.005 for Word Overlap; 0.011 for Spelling ErrorImproved
Train InferSent with swapped sentence pairs (ablation)InferSent sentence embeddings · NLP transfer taskstask metric: MR 76.92 -> 77.3; CR 78.15 -> 79.84; MPQA 87.64 -> 87.72; SUBJ 90.79 -> 90.99; TREC 83.6 -> 85; SICK-E 82.3 -> 83.24; SIMixed

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