9 citations · 9 across the 8 of their papers we have counts for
8 papers
Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
Arush Tagade, Shaoheng Zhou, Jiaxin Wen +1
Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's…
LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components
Hikaru Tsujimura, Arush Tagade
Large Language Models (LLMs) often display overconfidence, presenting information with unwarranted certainty in high-stakes contexts. We investigate the internal basis of this beha…
Explaining Surface Layer Theory Departures in Marine Flux Profiles with Data-Driven Discovery
Jack Foxabbott, Leo Mckee-Reid, Andrew Cusick +8
Monin--Obukhov Similarity Theory (MOST), which underpins nearly all bulk estimates of surface fluxes in the atmospheric surface layer, assumes monotonic wind profiles and verticall…
Benchmarking the Discovery Engine
Jack Foxabbott, Arush Tagade, Andrew Cusick +6
The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and r…
The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability
Stephen Casper, Jieun Yun, Joonhyuk Baek +13
Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying…
Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
Rusheb Shah, Quentin Feuillade--Montixi, Soroush Pour +3
Despite efforts to align large language models to produce harmless responses, they are still vulnerable to jailbreak prompts that elicit unrestricted behaviour. In this work, we in…
Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability
Arush Tagade, Jessica Rumbelow
We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We…
Why do CNNs excel at feature extraction? A mathematical explanation
Vinoth Nandakumar, Arush Tagade, Tongliang Liu
Over the past decade deep learning has revolutionized the field of computer vision, with convolutional neural network models proving to be very effective for image classification b…