3 citations · 3 across the 10 of their papers we have counts for
10 papers
The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs
Eric Yeats, Brendan Kennedy, Loc Truong +5
The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of inp…
What do Geometric Hallucination Detection Metrics Actually Measure?
Eric Yeats, John Buckheit, Sarah Scullen +9
Hallucination remains a barrier to deploying generative models in high-consequence applications. This is especially true in cases where external ground truth is not readily availab…
Saddle-Free Guidance: Improved On-Manifold Sampling without Labels or Additional Training
Eric Yeats, Darryl Hannan, Wilson Fearn +3
Score-based generative models require guidance in order to generate plausible, on-manifold samples. The most popular guidance method, Classifier-Free Guidance (CFG), is only applic…
A Connection Between Score Matching and Local Intrinsic Dimension
Eric Yeats, Aaron Jacobson, Darryl Hannan +4
The local intrinsic dimension (LID) of data is a fundamental quantity in signal processing and learning theory, but quantifying the LID of high-dimensional, complex data has been a…
Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
Eric Yeats, Darryl Hannan, Henry Kvinge +2
Machine unlearning (MU) is a promising cost-effective method to cleanse undesired information (generated concepts, biases, or patterns) from foundational diffusion models. While MU…
Do Counterfactual Examples Complicate Adversarial Training?
Eric Yeats, Cameron Darwin, Eduardo Ortega +2
We leverage diffusion models to study the robustness-performance tradeoff of robust classifiers. Our approach introduces a simple, pretrained diffusion method to generate low-norm…
Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Jingyang Zhang, Jingwei Sun, Eric Yeats +5
The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and t…
Adversarial Estimation of Topological Dimension with Harmonic Score Maps
Eric Yeats, Cameron Darwin, Frank Liu +1
Quantification of the number of variables needed to locally explain complex data is often the first step to better understanding it. Existing techniques from intrinsic dimension es…
Disentangling Learning Representations with Density Estimation
Eric Yeats, Frank Liu, Hai Li
Disentangled learning representations have promising utility in many applications, but they currently suffer from serious reliability issues. We present Gaussian Channel Autoencode…
NashAE: Disentangling Representations through Adversarial Covariance Minimization
Eric Yeats, Frank Liu, David Womble +1
We present a self-supervised method to disentangle factors of variation in high-dimensional data that does not rely on prior knowledge of the underlying variation profile (e.g., no…