Introduces a framework for measuring sycophantic praise in LLMs that outperforms generic judges and occurs more in social domains.
I’ve been wrestling with conflicting thoughts on this topic
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Author proposes adversarial co-thinking as a method of calibrating and triangulating multiple GenAI tools to generate critique during academic paper drafting, based on personal parallel use of Claude, ChatGPT, and Gemini.
Empirical study of 21k conversations finds human-like behaviors pervasive in LLMs but varying by model and user factors, with differing human judgments on appropriateness and partial controllability via prompts.
citing papers explorer
-
Sycophantic Praise: Evaluating Excessive Praise in Language Models
Introduces a framework for measuring sycophantic praise in LLMs that outperforms generic judges and occurs more in social domains.