← 研踪 PaperTrailarXiv:2611.01332 · v1
Large language models underrepresent malice and overreport virtue
首次提交 2026-11-01 06:56
版本更新 2026-11-01 06:56
雷达观测 2026-11-04 23:43
摘要
People increasingly use large language models (LLMs) to interpret others' behaviour, often assuming that LLMs infer motives as humans do. Aligned LLMs attribute more benevolent and less malevolent motives to a whistleblower than humans do, but ratings alone cannot reveal whether these differences arise in internal representations or at report. Here we compare linear-probe readouts of LLMs' internal states with their own ratings at the same prompt position for four motives, in two preregistered studies. For the two malevolent motives, self-interest and intent to harm, internal and expressed readouts did not differ: the lower ratings reflect weaker signal along the probed directions, not suppression at output. For the two benevolent motives, duty and concern for others, expressed ratings exceeded the internal readouts, indicating amplification at report. In free text the model rarely volunteered a motive against the colleague, far less often than humans did, yet produced one readily once the scenario supplied a reason. Shifting the internal representation along a malevolent-motive direction brought both malevolent ratings to the human level, whereas the rating of duty yielded only past a threshold at which the other motives had overshot. LLMs' more charitable motive profile thus has two distinct sources: reduced malevolent signal in the probed representation and amplified benevolent attribution at report.
作者备注：41 pages, 5 figures, 5 Extended Data figures, 2 Extended Data tables; Supplementary Information included
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 · 2026-11-01 06:56 · 最新观测版本
Large language models underrepresent malice and overreport virtue
People increasingly use large language models (LLMs) to interpret others' behaviour, often assuming that LLMs infer motives as humans do. Aligned LLMs attribute more benevolent and less malevolent motives to a whistleblower than humans do, but ratings alone cannot reveal whether these differences arise in internal representations or at report. Here we compare linear-probe readouts of LLMs' internal states with their own ratings at the same prompt position for four motives, in two preregistered studies. For the two malevolent motives, self-interest and intent to harm, internal and expressed readouts did not differ: the lower ratings reflect weaker signal along the probed directions, not suppression at output. For the two benevolent motives, duty and concern for others, expressed ratings exceeded the internal readouts, indicating amplification at report. In free text the model rarely volunteered a motive against the colleague, far less often than humans did, yet produced one readily once the scenario supplied a reason. Shifting the internal representation along a malevolent-motive direction brought both malevolent ratings to the human level, whereas the rating of duty yielded only past a threshold at which the other motives had overshot. LLMs' more charitable motive profile thus has two distinct sources: reduced malevolent signal in the probed representation and amplified benevolent attribution at report.
查看此版本解读 →查看此版本原文 ↗