8 papers
Token Rankings are Unforgeable Language Model Signatures
Matthew Finlayson, Andreas Grivas, Xiang Ren +1
Language model parameters are known to impose unique (to each model) geometric constraints on their logit outputs, which serves as a signature that identifies the model, but also l…
Side-by-side Comparison Amplifies Dialect Bias in Language Models
Kritee Kondapally, Claire J. Smerdon, Pooja C. Patel +5
Language models (LMs) can exhibit biases based on variations in their dialects, even in the absence of a dialect label, a behavior known as covert dialect bias. In this work, we qu…
Every Language Model Has a Forgery-Resistant Signature
Matthew Finlayson, Xiang Ren, Swabha Swayamdipta
The ubiquity of closed-weight language models with public-facing APIs has generated interest in forensic methods, both for extracting hidden model details (e.g., parameters) and fo…
Better Language Model Inversion by Compactly Representing Next-Token Distributions
Murtaza Nazir, Matthew Finlayson, John X. Morris +2
Language model inversion seeks to recover hidden prompts using only language model outputs. This capability has implications for security and accountability in language model deplo…
Teaching Models to Understand (but not Generate) High-risk Data
Ryan Wang, Matthew Finlayson, Luca Soldaini +2
Language model developers typically filter out high-risk content -- such as toxic or copyrighted text -- from their pre-training data to prevent models from generating similar outp…
Post-training an LLM for RAG? Train on Self-Generated Demonstrations
Matthew Finlayson, Ilia Kulikov, Daniel M. Bikel +3
Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training m…