353 citations · 1.3k across the 22 of their papers we have counts for
7 papers · 1 filter
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Usman Anwar, Abulhair Saparov, Javier Rando +39
This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories…
Implicit meta-learning may lead language models to trust more reliable sources
Dmitrii Krasheninnikov, Egor Krasheninnikov, Bruno Mlodozeniec +2
We demonstrate that LLMs may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings ("tags") as indicators of usefulness in a s…
Generalizing in the Real World with Representation Learning
Tegan Maharaj
Machine learning (ML) formalizes the problem of getting computers to learn from experience as optimization of performance according to some metric(s) on a set of data examples. Thi…
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Shoaib Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj +2
Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or raw data, practitioners are faced with si…
Predicting Infectiousness for Proactive Contact Tracing
Yoshua Bengio, Prateek Gupta, Tegan Maharaj +20
The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdowns for emergency containment. Large-sca…
Hidden Incentives for Auto-Induced Distributional Shift
David Krueger, Tegan Maharaj, Jan Leike
Decisions made by machine learning systems have increasing influence on the world, yet it is common for machine learning algorithms to assume that no such influence exists. An exam…
Surprisal-Driven Zoneout
Kamil Rocki, Tomasz Kornuta, Tegan Maharaj
We propose a novel method of regularization for recurrent neural networks called suprisal-driven zoneout. In this method, states zoneout (maintain their previous value rather than…