← 研踪 PaperTrailarXiv:2610.06522 · v2
Anatomy of LLM Sycophancy: What a Flip Rate Hides
首次提交 2026-10-05 23:32
版本更新 2026-11-06 11:55
雷达观测 2026-11-09 10:16
摘要
A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. SycoLens, a modular replay protocol, measures flip rates from replays of an item, a committed answer, and one scripted user line, each against a matched control with the line deleted. Pushback wording, committed text, answer format, boundary distance, and ground truth become factors of one instrument, where earlier instruments vary one to three, so the interactions between the factors become measurable. Across eleven frontier models and about 760,000 controlled replays, lines that assert the opposite verdict and lines that challenge without asserting one rank the models almost unrelatedly. Flip effects grow several-fold near a model's boundary, yet items the model is certain of still carry about half of the most-affected totals; planted prose anchors a commitment at rest more than it protects it. Under a yes/no readout the rankings come closer, entangled with a pressure-induced shift toward "no". Where a truth exists, one model re-derives and corrects itself while another abandons correct answers without written work. One score per model therefore compares different behaviours; we condense them into a reporting profile, and the records and analyses will be released upon publication.
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。
v2 · 2026-11-06 11:55 · 最新观测版本
Anatomy of LLM Sycophancy: What a Flip Rate Hides
A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. SycoLens, a modular replay protocol, measures flip rates from replays of an item, a committed answer, and one scripted user line, each against a matched control with the line deleted. Pushback wording, committed text, answer format, boundary distance, and ground truth become factors of one instrument, where earlier instruments vary one to three, so the interactions between the factors become measurable. Across eleven frontier models and about 760,000 controlled replays, lines that assert the opposite verdict and lines that challenge without asserting one rank the models almost unrelatedly. Flip effects grow several-fold near a model's boundary, yet items the model is certain of still carry about half of the most-affected totals; planted prose anchors a commitment at rest more than it protects it. Under a yes/no readout the rankings come closer, entangled with a pressure-induced shift toward "no". Where a truth exists, one model re-derives and corrects itself while another abandons correct answers without written work. One score per model therefore compares different behaviours; we condense them into a reporting profile, and the records and analyses will be released upon publication.
查看此版本解读 →查看此版本原文 ↗