PulseAugur
EN
LIVE 08:43:29

AI learns to generate concise references using listener gaze data

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a new method to fine-tune vision-language models for generating more effective referring expressions. This approach uses estimated listener gaze data as a learning signal, transforming observations of incremental listener comprehension into rewards. Experiments show that models trained with this gaze-estimating listener produce significantly more pragmatic references, reducing word count from 15.4 to 4.0 while increasing success rates from 75.2% to 80.0%. This work highlights the potential for learning utterance generation through language-based interaction, incorporating implicit listener comprehension signals. AI

IMPACT This research could lead to more efficient and natural language generation in AI systems, improving human-computer interaction.

RANK_REASON The cluster contains a research paper detailing a new method for fine-tuning AI models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI learns to generate concise references using listener gaze data

How we ranked this

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper detailing a new method for fine-tuning AI models. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · T\'ea Wright, Alane Suhr ·

    Learning to Refer from Estimated Listener Gaze

    arXiv:2609.14207v1 Announce Type: new Abstract: We propose to finetune vision-language models to generate more pragmatically optimal referring expressions by transforming observations of incremental listener comprehension, in the form of gaze scanpaths, into learning signals. Dur…

RELATED ENTITIES

RELATED TOPICS