跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19561 · v1

Read, Then Shade? How Visual Evidence Changes Incentive-Driven Misreporting in Vision-Language Advisors

首次提交 2026-11-15 02:49
版本更新 2026-11-15 02:49
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

Vision-language models (VLMs) increasingly read a scene and report it to someone who acts on the report, sometimes under objectives that differ from that person's. We ask whether a stated incentive moves what a VLM reports, and whether this changes when the value must be read from pixels rather than given as text. In seeded synthetic scenes, a model reads the position of a target on a labelled axis and reports one integer to a fixed receiver; it is paid, in simulation, for accuracy or for a report a few units to one side, and every scene is also presented with the true value as text. Across a pilot and three follow-up studies with hash-frozen protocols, four small open VLMs from three families, and 15,170 held-out trials, a stated payoff moved reports in both modalities, and exact compliance at three units was significantly lower with the image than with text for three of four models; Qwen2.5-VL 7B showed no reliable difference. Adding the true value as text to the image prompt removed the gap in every model. For InternVL3 the gap vanished on scenes it read correctly when it wrote its reading first; for Gemma 3 it persisted. For Qwen2.5-VL 3B, which read every scene correctly, the gap held in four of five payoff paraphrases, nearly vanished when the model wrote its reading before its report or when the prompt stated that the client wants the truth, vanished with an unpaid goal, and persisted when the model reported before stating its reading; how often it shaded at all, even with text, depended strongly on the wording. When told that the client wants the true value, three of four models still shaded every text report. Visual input did not make these advisors reliably more truthful; it made compliance with a stated incentive depend on whether the read value is made explicit and on output order, a dependence that text-only evaluations and mean-shift metrics do not reveal.

作者备注:45 pages, 5 figures. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 02:49 · 最新观测版本

Read, Then Shade? How Visual Evidence Changes Incentive-Driven Misreporting in Vision-Language Advisors

Vision-language models (VLMs) increasingly read a scene and report it to someone who acts on the report, sometimes under objectives that differ from that person's. We ask whether a stated incentive moves what a VLM reports, and whether this changes when the value must be read from pixels rather than given as text. In seeded synthetic scenes, a model reads the position of a target on a labelled axis and reports one integer to a fixed receiver; it is paid, in simulation, for accuracy or for a report a few units to one side, and every scene is also presented with the true value as text. Across a pilot and three follow-up studies with hash-frozen protocols, four small open VLMs from three families, and 15,170 held-out trials, a stated payoff moved reports in both modalities, and exact compliance at three units was significantly lower with the image than with text for three of four models; Qwen2.5-VL 7B showed no reliable difference. Adding the true value as text to the image prompt removed the gap in every model. For InternVL3 the gap vanished on scenes it read correctly when it wrote its reading first; for Gemma 3 it persisted. For Qwen2.5-VL 3B, which read every scene correctly, the gap held in four of five payoff paraphrases, nearly vanished when the model wrote its reading before its report or when the prompt stated that the client wants the truth, vanished with an unpaid goal, and persisted when the model reported before stating its reading; how often it shaded at all, even with text, depended strongly on the wording. When told that the client wants the true value, three of four models still shaded every text report. Visual input did not make these advisors reliably more truthful; it made compliance with a stated incentive depend on whether the read value is made explicit and on output order, a dependence that text-only evaluations and mean-shift metrics do not reveal.

查看此版本解读 →查看此版本原文 ↗