4 citations · 5 across the 5 of their papers we have counts for
7 papers
Tracing mechanisms of sycophantic agreement in language models
Sixing Chen, Zhuofan Josh Ying, Logan Riggs Smith +2
Sycophantic agreement in language models refers to the tendency to overly affirm a user's stated beliefs or preferences, often at the expense of factual accuracy. Although it is wi…
Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
Camila Blank, Zhuofan Ying, Christopher Potts +2
Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-kno…
Comparing Linear Probes with Mahalanobis Cosine Similarity
Zhuofan Josh Ying, Peter Hase, Nikolaus Kriegeskorte
Linear probes are widely used in interpretability research and often compared by cosine similarity. The Mahalanobis cosine similarity (MCS) between two directions, which reweights…
The Truthfulness Spectrum Hypothesis
Zhuofan Josh Ying, Shauli Ravfogel, Nikolaus Kriegeskorte +1
Large language models (LLMs) have been reported to linearly encode truthfulness, yet recent work questions this finding's generality. We reconcile these views with the truthfulness…
Adaptive Contextual Perception: How to Generalize to New Backgrounds and Ambiguous Objects
Zhuofan Ying, Peter Hase, Mohit Bansal
Biological vision systems make adaptive use of context to recognize objects in new settings with novel contexts as well as occluded or blurry objects in familiar settings. In this…
VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives
Zhuofan Ying, Peter Hase, Mohit Bansal
Many past works aim to improve visual reasoning in models by supervising feature importance (estimated by model explanation techniques) with human annotations such as highlights of…
Can Deep Learning Recognize Subtle Human Activities?
Vincent Jacquot, Zhuofan Ying, Gabriel Kreiman
Deep Learning has driven recent and exciting progress in computer vision, instilling the belief that these algorithms could solve any visual task. Yet, datasets commonly used to tr…