With the increased deployment of large language models (LLMs), one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with a focus on filters to prevent the generation of unsafe information. Two natural points of intervention are the filtering of the input prompt before it reaches the model, and filtering the output after generation. Our main results demonstrate computational challenges in filtering both prompts and outputs. First, we show that there exist LLMs for which there are no efficient prompt filters: adversarial prompts that… Read More
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
With the increased deployment of large language models (LLMs), one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with a focus on filters to prevent the generation of unsafe information. Two natural points of intervention are the filtering of the input prompt before it reaches the model, and filtering the output after generation. Our main results demonstrate computational challenges in filtering both prompts and outputs. First, we show that there exist LLMs for which there are no efficient prompt filters: adversarial prompts that…
Related Posts
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment
Query Auto-Completion (QAC) is a critical feature of modern search systems that improves search efficiency…
“Robot, make me a chair”
An AI-driven system lets users design and build simple, multicomponent objects by describing them with…
New research from Google Workspace reveals how young leaders are using AI at work.
Google Workspace has released findings from our second survey that looks at how people aged…