English(EN) Learning to Refer from Estimated Listener Gaze

AI学习使用听者注视数据生成简洁引用

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一种新方法，用于微调视觉语言模型以生成更有效的指代表达。该方法使用估计的听者注视数据作为学习信号，将渐进式听者理解的观察转化为奖励。实验表明，使用这种注视估计听者训练的模型生成的引用更具实用性，词数从15.4减少到4.0，成功率从75.2%提高到80.0%。这项工作强调了通过语言互动学习话语生成，并融入隐式听者理解信号的潜力。 AI

影响这项研究可能带来更高效、更自然的AI系统语言生成，改善人机交互。

排序理由该集群包含一篇详细介绍AI模型微调新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 18 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI模型微调新方法的论文。[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.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · T\'ea Wright, Alane Suhr · 2026-09-15 04:00

从估计的听者注视中学习引用

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…

本文如何被排名

报道来源 [1]

从估计的听者注视中学习引用

相关实体

相关话题