Search Results for author:
Found 3 papers, 3 papers with code
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
In this work, we introduce $\textit{weak-to-strong search}$, framing the alignment of a large language model as a test-time greedy search to maximize the log-likelihood difference between small tuned and untuned models while sampling from the frozen large model.
Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans.
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
Large Language Models (LLMs) are now commonplace in conversation applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
