Yangsibo Huang

Scaling Embedding Layers in Language Models

Quantifying Cross-Modality Memorization in Vision-Language Models

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

On Evaluating the Durability of Safeguards for Open-Weight LLMs

GMValuator: Similarity-based Data Valuation for Generative Models

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

Scaling Laws for Differentially Private Language Models

Scaling Embedding Layers in Language Models

On Memorization of Large Language Models in Logical Reasoning

Fantastic Copyrighted Beasts and How (Not) to Generate Them

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Detecting Pretraining Data from Large Language Models

LabelDP-Pro: Learning with Label Differential Privacy via Projections