Related papers: Neurobiber: Fast and Interpretable Stylistic Featu…

Missing values in high-dimensional, mixed-type datasets pose significant challenges for data imputation, particularly under Missing Not At Random (MNAR) mechanisms. Existing methods struggle to integrate local and global data…

An aesthetics evaluation model is at the heart of predicting users' aesthetic experience and developing user interfaces with higher quality. However, previous methods on aesthetic evaluation largely ignore the interpretability of the model…

Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional probing or surrogate model is used to interpret an existing…

Discovering interpretable patterns for classification of sequential data is of key importance for a variety of fields, ranging from genomics to fraud detection or more generally interpretable decision-making. In this paper, we propose a…

Neural Style Transfer has shown very exciting results enabling new forms of image manipulation. Here we extend the existing method to introduce control over spatial location, colour information and across spatial scale. We demonstrate how…

Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLMs) lack interpretability and controllability, often ignoring…

We present minicons, an open source library that provides a standard API for researchers interested in conducting behavioral and representational analyses of transformer-based language models (LMs). Specifically, minicons enables…

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel…

We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code. We test MIPS on a…

A program is characterized by its input model, and a formal input model can be of use in diverse areas including vulnerability analysis, reverse engineering, fuzzing and software testing, clone detection and refactoring. Unfortunately,…

We introduce bipol, a new metric with explainability, for estimating social bias in text data. Harmful bias is prevalent in many online sources of data that are used for training machine learning (ML) models. In a step to address this…

Fast expansion of natural language functionality of intelligent virtual agents is critical for achieving engaging and informative interactions. However, developing accurate models for new natural language domains is a time and data…

This paper creates a novel method of deep neural style transfer by generating style images from freeform user text input. The language model and style transfer model form a seamless pipeline that can create output images with similar losses…

The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from…

As artificial intelligence becomes increasingly pervasive and powerful, the ability to audit AI-based systems is growing in importance. However, explainability for artificial intelligence systems is not a one-size-fits-all solution;…

Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…

A key goal of current mechanistic interpretability research in NLP is to find linear features (also called "feature vectors") for transformers: directions in activation space corresponding to concepts that are used by a given model in its…

Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must…

Complex feature extractors are widely employed for text representation building. However, these complex feature extractors make the NLP systems prone to overfitting especially when the downstream training datasets are relatively small,…

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…