Boyi Wei
4 papers · 2024–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
harmful content
(1)
safety alignment
(1)
safety evaluation
(1)
fine tuning
(1)
model customization
(1)
open-weight model
(1)
model safeguard
(1)
unsafe content
(1)
copyright takedown
(1)
decoding-time intervention
(1)
safety refusal
(1)
pruning
(1)
brittleness
(1)
jailbreaking
(1)
adversarial robustness
(1)
low-rank modifications
(1)
Papers
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
ICLR 2025
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
ICML 2024
Evaluating Copyright Takedown Methods for Language Models
NeurIPS 2024