198 citations · 234 across the 9 of their papers we have counts for
9 papers
Scaling Inherently Interpretable Language Models
Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7
Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods whose reliability is difficult…
New Faithfulness-Centric Interpretability Paradigms for Natural Language Processing
Andreas Madsen
As machine learning becomes more widespread and is used in more critical applications, it's important to provide explanations for these models, to prevent unintended behavior. Unfo…
Interpretability Needs a New Paradigm
Andreas Madsen, Himabindu Lakkaraju, Siva Reddy +1
Interpretability is the study of explaining models in understandable terms to humans. At present, interpretability is divided into two paradigms: the intrinsic paradigm, which beli…
Are self-explanations from Large Language Models faithful?
Andreas Madsen, Sarath Chandar, Siva Reddy
Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanatio…
Faithfulness Measurable Masked Language Models
Andreas Madsen, Siva Reddy, Sarath Chandar
A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong…
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Andreas Madsen, Nicholas Meade, Vaibhav Adlakha +1
To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for making a prediction. However, an open questio…
Post-hoc Interpretability for Neural NLP: A Survey
Andreas Madsen, Siva Reddy, Sarath Chandar
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use. Explaining models helps to address…
Neural Arithmetic Units
Andreas Madsen, Alexander Rosenberg Johansen
Neural networks can approximate complex functions, but they struggle to perform exact arithmetic operations over real numbers. The lack of inductive bias for arithmetic operations…
Measuring Arithmetic Extrapolation Performance
Andreas Madsen, Alexander Rosenberg Johansen
The Neural Arithmetic Logic Unit (NALU) is a neural network layer that can learn exact arithmetic operations between the elements of a hidden state. The goal of NALU is to learn pe…