Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence

Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence 待解读

下载

可分享卡片

适合发到公众号、飞书、社群群发，帮助团队复用高质量解读。

Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence
作者: Yunuo Wang, Maoyuan Chen, Yuanjin Huang, Xing Liu

For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We compare matched same-class and different-class replac…

详情页: https://www.ourxiv.cn/2610.37605v1

分享到 X

新用户看这篇论文该怎么开始

先点「赞助解读」，AI 会把论文转成可直接执行的行动清单。
看完“可执行改进行动”后，可快速决定是否值得立项。
用上面的卡片内容直接发给团队，减少重复阅读。

先订阅关键词，后续不再手工筛论文

摘要

For audio-language models, an answer change after a local sound-event edit can reflect a response to the event's class, sensitivity to waveform rewriting, or both. We compare matched same-class and different-class replacements of a queried event. Both use the same interval, level estimate, donor fitting, and crossfade, while the same-class replacement preserves the correct answer. Across 600 synthetic soundscapes and three models from two architecture families, different-class replacements produce 49.7 to 60.9 percentage points more answer changes than same-class replacements. Same-class accuracy remains within 5.2 percentage points of original accuracy. Among trials with correct original and same-class answers, soundscape-weighted selective accuracy for the inserted class is 73.7 to 81.9%, averaging eligible trials within each soundscape and then weighting eligible soundscapes equally. This protocol tests how model answers respond to local changes in event class.

分析报告

暂无报告。点击“分析”开始生成。

个性化解读与社区共享解读不同

用自己的话告诉 AI 你想要什么样的解读（比如"用大白话讲给非专业人士听"、"重点分析对我们团队 RAG 系统的可迁移性"），生成一份只属于你自己的版本；生成后也可以选择设为"愿意共享"，被更多人看到、点赞。