31 citations · 43 across the 10 of their papers we have counts for
4 papers · 1 filter
Position: LLM Unlearning Benchmarks are Weak Measures of Progress
Pratiksha Thaker, Shengyuan Hu, Neil Kale +3
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning re…
AI Governance and Accountability: An Analysis of Anthropic's Claude
Aman Priyanshu, Yash Maurya, Zuofei Hong
As AI systems become increasingly prevalent and impactful, the need for effective AI governance and accountability measures is paramount. This paper examines the AI governance land…
Unified Locational Differential Privacy Framework
Aman Priyanshu, Yash Maurya, Suriya Ganesh +1
Aggregating statistics over geographical regions is important for many applications, such as analyzing income, election results, and disease spread. However, the sensitive nature o…
Guardrail Baselines for Unlearning in LLMs
Pratiksha Thaker, Yash Maurya, Shengyuan Hu +2
Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both gen…