# Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

arXiv: https://arxiv.org/abs/2305.18213 · HTML: https://mlsanity.com/paper/2305.18213/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Information-Theoretic Probing with Minimum Description Length](https://mlsanity.com/paper/2003.12298/) (2020)
- [Information-Theoretic Probing for Linguistic Structure](https://mlsanity.com/paper/2004.03061/) (2020)
- [A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection](https://mlsanity.com/paper/2106.09022/) (2021)
- [Max-value Entropy Search for Efficient Bayesian Optimization](https://mlsanity.com/paper/1703.01968/) (2017)
- [A Theory of Usable Information Under Computational Constraints](https://mlsanity.com/paper/2002.10689/) (2020)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (2020)
- [Plex: Towards Reliability using Pretrained Large Model Extensions](https://mlsanity.com/paper/2207.07411/) (2022)
- [Pre-trained Gaussian Processes for Bayesian Optimization](https://mlsanity.com/paper/2109.08215/) (2021)
- [Conditional probing: measuring usable information beyond a baseline](https://mlsanity.com/paper/2109.09234/) (2021)
- [Probing for the Usage of Grammatical Number](https://mlsanity.com/paper/2204.08831/) (2022)
- [Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification](https://mlsanity.com/paper/1805.10915/) (2018)

## Built on by (most cited first, 11 of 11)

- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing](https://mlsanity.com/paper/2410.06331/) (2024)
- [Challenges with unsupervised LLM knowledge discovery](https://mlsanity.com/paper/2312.10029/) (2023)
- [Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty](https://mlsanity.com/paper/2412.06771/) (2024)
- [Bayes in the age of intelligent machines](https://mlsanity.com/paper/2311.10206/) (2023)
- [InversionView: A General-Purpose Method for Reading Information from Neural Activations](https://mlsanity.com/paper/2405.17653/) (2024)
- [Probing the Category of Verbal Aspect in Transformer Language Models](https://mlsanity.com/paper/2406.02335/) (2024)
- [Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?](https://mlsanity.com/paper/2505.18575/) (2025)
- [Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations](https://mlsanity.com/paper/2605.16405/) (2026)
- [Likelihood approximations via Gaussian approximate inference](https://mlsanity.com/paper/2410.20754/) (2024)
- [Example-Based Concept Analysis Framework for Deep Weather Forecast Models](https://mlsanity.com/paper/2504.00831/) (2025)

## Abstract (arXiv)

Understanding which concepts models can and cannot represent has been fundamental to many tasks: from effective and responsible use of models to detecting out of distribution data. We introduce Gaussian process probes (GPP), a unified and simple framework for probing and measuring uncertainty about concepts represented by models. As a Bayesian extension of linear probing methods, GPP asks what kind of distribution over classifiers (of concepts) is induced by the model. This distribution can be used to measure both what the model represents and how confident the probe is about what the model represents. GPP can be applied to any pre-trained model with vector representations of inputs (e.g., activations). It does not require access to training data, gradients, or the architecture. We validate GPP on datasets containing both synthetic and real images. Our experiments show it can (1) probe a model's representations of concepts even with a very small number of examples, (2) accurately measure both epistemic uncertainty (how confident the probe is) and aleatory uncertainty (how fuzzy the concepts are to the model), and (3) detect out of distribution data using those uncertainty measures as well as classic methods do. By using Gaussian processes to expand what probing can offer, GPP provides a data-efficient, versatile and uncertainty-aware tool for understanding and evaluating the capabilities of machine learning models.