Related papers: Interpreto: An Explainability Library for Transfor…

Interpretability is the study of explaining models in understandable terms to humans. At present, interpretability is divided into two paradigms: the intrinsic paradigm, which believes that only models designed to be explained can be…

In the rapidly evolving landscape of artificial intelligence, multi-modal large language models are emerging as a significant area of interest. These models, which combine various forms of data input, are becoming increasingly popular.…

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed. However, how to take action to address these patterns is not always…

The HuggingFace Datasets Hub hosts thousands of datasets, offering exciting opportunities for language model training and evaluation. However, datasets for a specific task type often have different schemas, making harmonization challenging.…

Face Recognition (FR) has advanced significantly with the development of deep learning, achieving high accuracy in several applications. However, the lack of interpretability of these systems raises concerns about their accountability,…

adaptNMT is an open-source application that offers a streamlined approach to the development and deployment of Recurrent Neural Networks and Transformer models. This application is built upon the widely-adopted OpenNMT ecosystem, and is…

We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual…

Interpretability is crucial for building safe, reliable, and controllable language models, yet existing interpretability pipelines remain costly and difficult to scale. Interpreting a new model typically requires training model-specific…

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as semantic or stylistic structure. Each…

Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces Adaptor library that transposes the traditional model-centric approach composed of…

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…

While the state-of-the-art for frame semantic parsing has progressed dramatically in recent years, it is still difficult for end-users to apply state-of-the-art models in practice. To address this, we present Frame Semantic Transformer, an…

Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs' privileged access to their own internals can be leveraged…

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Data exploration is an important step of every data science and machine learning project, including those involving textual data. We provide a novel language tool, in the form of a publicly available Python library for extracting patterns…

Recent research demonstrates that external knowledge injection can advance pre-trained language models (PLMs) in a variety of downstream NLP tasks. However, existing knowledge injection methods are either applicable to structured knowledge…

The lack of a commonly used benchmark data set (collection) such as (Super-)GLUE (Wang et al., 2018, 2019) for the evaluation of non-English pre-trained language models is a severe shortcoming of current English-centric NLP-research. It…

The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the…