11 papers
Watermarking for Proprietary Dataset Protection
John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura +1
A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settings. We argue that output water…
Multi-Token Prediction via Self-Distillation
John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson +3
Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inferen…
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Sean McLeish, Ang Li, John Kirchenbauer +7
Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to co…
Gemstones: A Model Suite for Multi-Faceted Scaling Laws
Sean McLeish, John Kirchenbauer, David Yu Miller +5
Scaling laws are typically fit using a family of models with a narrow range of frozen hyperparameter choices. In this work we study scaling laws using multiple architectural shapes…
Zero-Shot Vision Encoder Grafting via LLM Surrogates
Kaiyu Yue, Vasu Singla, Menglin Jia +6
Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden…
RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
Bang An, Shiyue Zhang, Mark Dredze
Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented…