Search Results for author:
Found 7 papers, 3 papers with code
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs.
Corrective Machine Unlearning
We hope our work spurs research towards developing better methods for corrective unlearning and offers practitioners a new strategy to handle data integrity challenges arising from web-scale training.
Representation Engineering: A Top-Down Approach to AI Transparency
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience.
Ranked #3 on
Question Answering
on TruthfulQA
Proportional Aggregation of Preferences for Sequential Decision Making
In each round, a decision rule must choose a decision from a set of alternatives where each voter reports which of these alternatives they approve.
Low impact agency: review and discussion
Powerful artificial intelligence poses an existential threat if the AI decides to drastically change the world in pursuit of its goals.
Towards Adversarial Evaluations for Inexact Machine Unlearning
Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias.
From Pivots to Graphs: Augmented CycleDensity as a Generalization to One Time InverseConsultation
This paper describes an approach used to generate new translations using raw bilingual dictionaries as part of the 4th Task Inference Across Dictionaries (TIAD 2021) shared task.
