6 citations · 6 across the 11 of their papers we have counts for
11 papers
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
MathAtlas: A Benchmark for Autoformalization in the Wild
Nilay Patel, Noah Arias, Davit Babayan +7
Current autoformalization benchmarks are largely focused on olympiad or undergraduate mathematics, while graduate and research-level mathematics remains underexplored. In this pape…
Residual Matrix Transformers: Scaling the Size of the Residual Stream
Brian Mak, Jeffrey Flanigan
The residual stream acts as a memory bus where transformer layers both store and access features (Elhage et al., 2021). We consider changing the mechanism for retrieving and storin…
Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages
Christopher Toukmaji, Jeffrey Flanigan
LLMs are typically trained in high-resource languages, and tasks in lower-resourced languages tend to underperform the higher-resource language counterparts for in-context learning…
RAC: Efficient LLM Factuality Correction with Retrieval Augmentation
Changmao Li, Jeffrey Flanigan
Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This…
Large Language Model Unlearning via Embedding-Corrupted Prompts
Chris Yuhao Liu, Yaxuan Wang, Jeffrey Flanigan +1
Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ens…
Future Language Modeling from Temporal Document History
Changmao Li, Jeffrey Flanigan
Predicting the future is of great interest across many aspects of human activity. Businesses are interested in future trends, traders are interested in future stock prices, and com…
Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel
Brendan King, Jeffrey Flanigan
Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step.…
Task Contamination: Language Models May Not Be Few-Shot Anymore
Changmao Li, Jeffrey Flanigan
Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. However, their success in zero-shot and few-shot settings may be affected by task…
Understanding the Role of Optimization in Double Descent
Chris Yuhao Liu, Jeffrey Flanigan
The phenomenon of model-wise double descent, where the test error peaks and then reduces as the model size increases, is an interesting topic that has attracted the attention of re…
A New Approach Towards Autoformalization
Nilay Patel, Rahul Saha, Jeffrey Flanigan
Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language math…