AI Paper Atlas

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

Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention

Sounak Mondal, Dimitris Samaras, Gregory Zelinsky, Minh Hoai Nguyen

ECCV 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 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
add ThinkAloud auxiliary task (ablation)Gazette · RefCOCO-Gaze object referral (Task A)CIDEr: 0.872 -> 0.974Improved
add ThinkAloud auxiliary task (ablation)Gazette · RefCOCO-Gaze object referral (Task A)BLEU-4: 0.070 -> 0.098Improved
add ThinkAloud auxiliary task (ablation)Gazette · AiR-D VQA (Task B)CIDEr: 0.263 -> 0.367 (+39.54%)Improved
add ThinkAloud auxiliary task (ablation)Gazette · AiR-D VQA (Task B)BLEU-4: 0.095 -> 0.159 (+67.37%)Improved
add ThinkAloud auxiliary task (ablation)Gazette · RefCOCO-Gaze object referral (Task A)GPT-4 judge Expression Overlap: 5.019 -> 5.980Improved
add ThinkAloud auxiliary task (ablation)Gazette · AiR-D VQA (Task B)GPT-4 judge Answer Equivalence: 1.642 -> 2.135Improved
add ThinkAloud auxiliary task (ablation)Gazette · COCO-Search18 target-present search (Task C)accuracy: 0.742 -> 0.773Improved
add ThinkAloud auxiliary task (ablation)Gazette · COCO-Search18 target-absent search (Task D)accuracy: 0.445 -> 0.443No clear effect
add LLaVA-last style last-fixation baseline instead of full scanpathLLaVA-1.5-7B · RefCOCO-Gaze object referral (Task A)CIDEr: 0.974 -> 0.113Hurt
add attention allocation explanation (GenAttAlloc) alone vs target localization and fixation count (full set) (ablation)Gazette · RefCOCO-Gaze object referral (Task A)CIDEr: 0.838 -> 0.974Improved
add LocTarget and CountFix to GenAttAlloc-only transcript (ablation)Gazette · AiR-D VQA (Task B)CIDEr: 0.433 -> 0.367Hurt
add LocTarget and CountFix to GenAttAlloc-only transcript (ablation)Gazette · COCO-Search18 target-present search (Task C)accuracy: 0.686 -> 0.773Improved

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