AI Paper Atlas

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

Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention

Ekta Sood, Simon Tannert, Philipp Mueller, Andreas Bulling

NeurIPS 2020 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 37 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
Integrate TSM gaze predictions into task attention and jointly adapt the TSMParaphrase generation · Quora Question Pairs, 100KBLEU-4: 17.9 -> 28.82Improved
Integrate TSM gaze predictions into task attention and jointly adapt the TSMParaphrase generation · Quora Question Pairs, 50KBLEU-4: 16.5 -> 26.24Improved
Integrate TSM gaze predictions into task attentionSentence compression · Google Sentence CompressionF1: 85.1 vs. 85.0No clear effect
Remove TSM fixation guidance (ablation)Joint task models · Quora Question Pairs, 50K and 100KBLEU-4: 26.24 -> 24.62; 28.82 -> 27.81Hurt
Replace hybrid-pretrained TSM initialization with random initialization (ablation)Joint task models · Quora Question Pairs and Google Sentence CompressionBLEU-4 / F1: 26.24 -> 25.26; 28.82 -> 27.11; 85.0 -> 83.7Hurt
Swap TSM weights between the upstream tasks (ablation)Joint task models · Quora Question Pairs and Google Sentence CompressionBLEU-4 / F1: 26.24 -> 23.43; 28.82 -> 27.60; 85.0 -> 83.8Hurt
Freeze TSM weights during joint task training (ablation)Joint task models · Quora Question Pairs and Google Sentence CompressionBLEU-4 / F1: 26.24 -> 25.73; 28.82 -> 28.26; 85.0 -> 83.9Hurt
Pre-train the TSM on E-Z Reader synthetic data before human-gaze training (ablation)Text Saliency Model · ProvoSpearman's ρ: 0.83* -> 0.88*Improved
Pre-train the TSM on E-Z Reader synthetic data before human-gaze training (ablation)Text Saliency Model · MQA-RCSpearman's ρ: 0.76* -> 0.94*Improved
Remove pre-training on E-Z Reader synthetic data (ablation)Text Saliency Model · Dundee, Provo + Geco, GecoSpearman's ρ: 0.99* -> 0.99*; 1.00* -> 0.99*; 0.99* -> 0.98*No clear effect
Remove fine-tuning on human gaze data (ablation)Text Saliency Model · Dundee, Provo + Geco, Provo, Geco, MQA-RCSpearman's ρ: 0.99* -> -0.68; 1.00* -> 0.10; 0.88* -> -0.25; 0.99* -> -0.10; 0.94* -> -0.05Hurt
Add E-Z Reader synthetic-data pre-training (ablation)Text Saliency Model · ProvoJSD: 0.44 to 0.24Improved

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