100 citations · 109 across the 13 of their papers we have counts for
15 papers
Language Model Activations Inhabit Privileged Error-Correcting Basins
Matthew Finlayson, Francisco Pernice, Eric Todd +16
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize t…
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…
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
Sean Welleck, Amanda Bertsch, Matthew Finlayson +5
One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has…
Logits of API-Protected LLMs Leak Proprietary Information
Matthew Finlayson, Xiang Ren, Swabha Swayamdipta
Large language model (LLM) providers often hide the architectural details and parameters of their proprietary models by restricting public access to a limited API. In this work we…
Closing the Curious Case of Neural Text Degeneration
Matthew Finlayson, John Hewitt, Alexander Koller +2
Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation fo…
Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy
Sarah Wiegreffe, Matthew Finlayson, Oyvind Tafjord +2
When pretrained language models (LMs) are applied to discriminative tasks such as multiple-choice questions, they place probability mass on vocabulary tokens that aren't among the…
Lila: A Unified Benchmark for Mathematical Reasoning
Swaroop Mishra, Matthew Finlayson, Pan Lu +8
Mathematical reasoning skills are essential for general-purpose intelligent systems to perform tasks from grocery shopping to climate modeling. Towards evaluating and improving AI…
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
Tushar Khot, Harsh Trivedi, Matthew Finlayson +4
Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or w…
What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
Matthew Finlayson, Kyle Richardson, Ashish Sabharwal +1
The instruction learning paradigm -- where a model learns to perform new tasks from task descriptions alone -- has become popular in general-purpose model research. The capabilitie…
Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
Matthew Finlayson, Aaron Mueller, Sebastian Gehrmann +3
Targeted syntactic evaluations have demonstrated the ability of language models to perform subject-verb agreement given difficult contexts. To elucidate the mechanisms by which the…