1 citations · 1 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
Tony T. Wang, John Hughes, Henry Sleight +7
Defending large language models against jailbreaks so that they never engage in a broadly-defined set of forbidden behaviors is an open problem. In this paper, we investigate the d…
cs.LG2023
Forbidden Facts: An Investigation of Competing Objectives in Llama-2
Tony T. Wang, Miles Wang, Kaivalya Hariharan +1
LLMs often face competing pressures (for example helpfulness vs. harmlessness). To understand how models resolve such conflicts, we study Llama-2-chat models on the forbidden fact…