Roger Baker Grosse

Associate Professor, Department of Computer Science, University of Toronto

4 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference

#3407 · Stephen Zhao, Aidan Li, Rob Brekelmans, Roger Baker Grosse

Poster Session 5

2 papers

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

#103 · Sang Keun Choe, Hwijeen Ahn, Juhan Bae, Kewen Zhao, Youngseog Chung, Adithya Pratapa, Willie Neiswanger, Emma Strubell, Teruko Mitamura, Jeff Schneider, Eduard Hovy, Roger Baker Grosse, Eric P. Xing

We scale the influence-function-based data valuation method to recent LLMs and their massive training datasets.

Distributional Training Data Attribution: What do Influence Functions Sample?

#3901 Spotlight · Bruno Kacper Mlodozeniec, Isaac Reid, Samuel Power, David Krueger, Murat A Erdogdu, Richard E. Turner, Roger Baker Grosse

This paper introduces distributional training data attribution, a data attribution framework that accounts for stochasticity in deep learning training, enabling a mathematical justification for why influence functions work in this setting.

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Better Training Data Attribution via Better Inverse Hessian-Vector Products

#3907 · Andrew Wang, Elisa Nguyen, Runshi Yang, Juhan Bae, Sheila A. McIlraith, Roger Baker Grosse

We apply the EKFAC-preconditioner on Neumann series iterations to arrive at an unbiased iHVP approximation for TDA that improves influence function and unrolled differentiation performance.