1 citations · 1 across the 4 of their papers we have counts for
4 papers · 1 filter
Sycophantic Praise: Evaluating Excessive Praise in Language Models
Daniel Vennemeyer, Phan Anh Duong, Meryl Ye +2
Sycophancy in language models is typically studied as excessive agreement or validation, while explicit praise and flattery have received comparatively little attention. We argue t…
Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
Daniel Vennemeyer, Phan Anh Duong, Tiffany Zhan +1
Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from…
Objective Matters: Fine-Tuning Objectives Shape Safety, Robustness, and Persona Drift
Daniel Vennemeyer, Punya Syon Pandey, Phan Anh Duong +2
Fine-tuning LLMs on benign data can still degrade alignment and adversarial robustness, yet direct analysis of the role of fine-tuning objectives in shaping these safety outcomes r…
GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models
Dylan Hutson, Daniel Vennemeyer, Aneesh Deshmukh +2
We introduce GuessingGame, a protocol for evaluating large language models (LLMs) as strategic question-askers in open-ended, open-domain settings. A Guesser LLM identifies a hidde…