11 citations · 38 across the 17 of their papers we have counts for
19 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
VaultGemma: A Differentially Private Gemma Model
Amer Sinha, Thomas Mesnard, Ryan McKenna +18
We introduce VaultGemma 1B, a 1 billion parameter model within the Gemma family, fully trained with differential privacy. Pretrained on the identical data mixture used for the Gemm…
Quantifying Cross-Modality Memorization in Vision-Language Models
Yuxin Wen, Yangsibo Huang, Tom Goldstein +3
Understanding what and how neural networks memorize during training is crucial, both from the perspective of unintentional memorization of potentially sensitive information and fro…
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
Kaixuan Huang, Jiacheng Guo, Zihao Li +15
Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieve…
Scaling Embedding Layers in Language Models
Da Yu, Edith Cohen, Badih Ghazi +5
We propose (calable, ontextualized, ffloaded, -gram mbedding), a new method for extending input embedding layers to enhance language model performance. To av…
Scaling Laws for Differentially Private Language Models
Ryan McKenna, Yangsibo Huang, Amer Sinha +9
Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hype…
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
Yangsibo Huang, Daogao Liu, Lynn Chua +7
Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expos…
On Memorization of Large Language Models in Logical Reasoning
Chulin Xie, Yangsibo Huang, Chiyuan Zhang +6
Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when…
An Adversarial Perspective on Machine Unlearning for AI Safety
Jakub Łucki, Boyi Wei, Yangsibo Huang +3
Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazard…
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Weijia Shi, Jaechan Lee, Yangsibo Huang +7
Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. Data owners may request the removal of their data from a trained…
Evaluating Copyright Takedown Methods for Language Models
Boyi Wei, Weijia Shi, Yangsibo Huang +5
Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content…
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
Lynn Chua, Badih Ghazi, Yangsibo Huang +6
Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e…
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Tinghao Xie, Xiangyu Qi, Yi Zeng +13
Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts…
Fantastic Copyrighted Beasts and How (Not) to Generate Them
Luxi He, Yangsibo Huang, Weijia Shi +7
Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns about copyright…
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
Lynn Chua, Badih Ghazi, Yangsibo Huang +6
Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive dat…
AI Risk Management Should Incorporate Both Safety and Security
Xiangyu Qi, Yangsibo Huang, Yi Zeng +22
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety…
A Safe Harbor for AI Evaluation and Red Teaming
Shayne Longpre, Sayash Kapoor, Kevin Klyman +20
Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by promi…
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Boyi Wei, Kaixuan Huang, Yangsibo Huang +6
Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This stu…
Sparsity-Preserving Differentially Private Training of Large Embedding Models
Badih Ghazi, Yangsibo Huang, Pritish Kamath +4
As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm th…