1 citations · 4 across the 16 of their papers we have counts for
9 papers · 1 filter
A Low-Rank Subspace Analysis of LLM Interventions
Angira Sharma, Christian Schroeder de Witt, Philip Torr +2
Interventions designed to modify a particular behavior in LLMs, such as refusal or sycophancy, often produce unintended changes in other behaviors. This lack of targeted control ma…
When Language Representations Interact: Separability and Cross-Lingual Effects in LLMs
Boris Marinov, Angira Sharma, Christian Schroeder de Witt +3
Large language models exhibit strong multilingual capabilities, however, their internal representations are difficult to interpret. Understanding these interactions is important fo…
Neural Network-Based Parameter Estimation of a Labour Market Agent-Based Model
M Lopes Alves, Joel Dyer, Doyne Farmer +2
Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in computational processing and storage have facilitated the adoption of ABMs across…
Bayesian Decision Making around Experts
Daniel Jarne Ornia, Joel Dyer, Nicholas Bishop +2
Complex learning agents are increasingly deployed alongside existing experts, such as human operators or previously trained agents. However, it remains unclear how should learners…
Sandbagging in a Simple Survival Bandit Problem
Joel Dyer, Daniel Jarne Ornia, Nicholas Bishop +2
Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify risks before deployment. However,…
Using causal abstractions to accelerate decision-making in complex bandit problems
Joel Dyer, Nicholas Bishop, Anisoara Calinescu +2
Although real-world decision-making problems can often be encoded as causal multi-armed bandits (CMABs) at different levels of abstraction, a general methodology exploiting the inf…
IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)
Siyi Sun, David Antony Selby, Yunchuan Huang +3
Missing data imputation in tabular datasets remains a pivotal challenge in data science and machine learning, particularly within socioeconomic research. However, real-world socioe…
SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
Constantin Venhoff, Anisoara Calinescu, Philip Torr +1
A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However,…
Causally Abstracted Multi-armed Bandits
Fabio Massimo Zennaro, Nicholas Bishop, Joel Dyer +4
Multi-armed bandits (MAB) and causal MABs (CMAB) are established frameworks for decision-making problems. The majority of prior work typically studies and solves individual MAB and…