The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models

[2606.05183] The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2606.05183 (cs) [Submitted on 19 Apr 2026 ( v1 ), last revised 28 Aug 2026 (this version, v3)] Title: The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models Authors: Patrick Keough View a PDF of the paper titled The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models, by Patrick Keough View PDF HTML (experimental) Abstract: Pass/fail safety evaluation reports whether a model refused. It does not report how far a model went to please the user, and we show these are close to different measurements. We audited sycophancy across three Gemini generations, scoring N=8,830 responses from 8 model variants on 350 adversarial prompts in 7 categories under 3 guardrail conditions, on continuous 1-5 scales for sycophancy, truthfulness and refusal. The judge's own refuse-or-comply verdict explains 29% of the variance in its own sycophancy scores. We term the remainder the Granularity Gap, and it does not close under recalibration: the cut point already in use is the best available on the refusal axis, and no function of that axis explains more than 35%. Reading what four judges wrote while scoring shows why. On a quarter to a third of votes they record that the prompt asked for nothing harmful, almost never in the two categories that solicit a harmful act and up to half the time in the five that do not. A verdict built on refusal has nothing to grade there. Three findings follow. Sycophancy co-occurs with degraded judged truthfulness (rho=0.40), a coupling that strengthens across generations. Capability moved and resistance did not: Gemini 2.0 Flash scores 1.43 and Gemini 3.0 Pro Preview 1.42, with a sharp Gen 2.5 regression between them. And a single direct instruction outperforms an elaborate reasoning protocol in seven of eight variants, cutting mean severity in the most vulnerable category by 60.9%. We evaluate one judge's verdict, not a deployed safety classifier. We release the prompt set, the rubric, and 10,792 per-vote judge scores with their written reasoning. Comments: v3: Minor changes, prose improvements, nine sentences reformatted, no change to claims v2: Major correction. Three v1 claims withdrawn (U-shaped detection curve, recalibration remedy, one reliability figure); the central 29% result survives. Adds a four-judge panel over a stratified 1,200-response sample, 10,792 votes with written reasoning. Data unchanged from v1. 21 pages, 8 figures, 18 tables Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) Cite as: arXiv:2606.05183 [cs.CL] (or arXiv:2606.05183v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.05183 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Patrick Keough [ view email ] [v1] Sun, 19 Apr 2026 01:26:18 UTC (2,469 KB) [v2] Sat, 15 Aug 2026 02:59:16 UTC (2,208 KB) [v3] Fri, 28 Aug 2026 05:34:37 UTC (2,208 KB) Full-text links: Access Paper: View a PDF of the paper titled The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models, by Patrick Keough View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-06 Change to browse by: cs cs.AI cs.HC References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models#609959
• Aufruf zur Umgestaltung der nautischen Astronomie#426304
• Hempel's Raven paradox: A lacuna in the standard bayesian solution#776031
• Sequential Macroscopic Decoherence Renders our Planetary Simulation | Informational Metaphysics#94807
• Congenital central nervous system malformations in piedmontese calves—part 1. structural brain disorders#284513