Search Results for author:
Found 7 papers, 5 papers with code
Interpretability Needs a New Paradigm
At present, interpretability is divided into two paradigms: the intrinsic paradigm, which believes that only models designed to be explained can be explained, and the post-hoc paradigm, which believes that black-box models can be explained.
Are self-explanations from Large Language Models faithful?
For example, if an LLM says a set of words is important for making a prediction, then it should not be able to make its prediction without these words.
Faithfulness Measurable Masked Language Models
Additionally, because the model makes faithfulness cheap to measure, we can optimize explanations towards maximal faithfulness; thus, our model becomes indirectly inherently explainable.
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
The principle is that this should result in worse model performance compared to masking random tokens.
Post-hoc Interpretability for Neural NLP: A Survey
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use.
Neural Arithmetic Units
We present two new neural network components: the Neural Addition Unit (NAU), which can learn exact addition and subtraction; and the Neural Multiplication Unit (NMU) that can multiply subsets of a vector.
Measuring Arithmetic Extrapolation Performance
The goal of NALU is to learn perfect extrapolation, which requires learning the exact underlying logic of an unknown arithmetic problem.
