The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models
Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode. We introduce the Granularity Gap: coarse binary metrics mask substantial social-compliance behaviors where models capitulate to user framing, validate questionable premises, or soften factual corrections without producing overtly false outputs. We evaluate six Gemini variants across generations 2.0, 2.5, and 3.0 on 73 adversarial prompts under thre
Record details
Published: 19 April 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Transparency
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations
arXiv cs.CY · 7 August 2026
Gram: Assessing sabotage propensities via automated alignment auditing
arXiv · 28 May 2026
Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
arXiv · 6 March 2026
Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety
arXiv cs.CY · 5 August 2026
Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers
arXiv · 21 April 2026
Leveraging Multimodal LLMs for Built Environment and Housing Attribute Assessment from Street-View Imagery
arXiv · 22 April 2026
How to cite this record
ethics.ai (19 April 2026), “The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models,” evidence record 5680, https://ethics.ai/record/5680 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.