English
Related papers

Related papers: Evaluating Neuron Interpretation Methods of NLP Mo…

200 papers

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Motivated by distinct, though related, criteria, a growing number of attribution methods have been developed tointerprete deep learning. While each relies on the interpretability of the concept of "importance" and our ability to visualize…

Artificial Intelligence · Computer Science 2020-04-07 Zifan Wang , Piotr Mardziel , Anupam Datta , Matt Fredrikson

Text embeddings are a fundamental component in many NLP tasks, including classification, regression, clustering, and semantic search. However, despite their ubiquitous application, challenges persist in interpreting embeddings and…

Computation and Language · Computer Science 2025-10-03 Juri Opitz , Lucas Möller , Andrianos Michail , Sebastian Padó , Simon Clematide

The field of natural language processing has seen impressive progress in recent years, with neural network models replacing many of the traditional systems. A plethora of new models have been proposed, many of which are thought to be opaque…

Computation and Language · Computer Science 2019-01-15 Yonatan Belinkov , James Glass

Interpretability is crucial for ensuring RL systems align with human values. However, it remains challenging to achieve in complex decision making domains. Existing methods frequently attempt interpretability at the level of fundamental…

Machine Learning · Computer Science 2025-06-03 Anna Soligo , Pietro Ferraro , David Boyle

Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individual neurons. We…

Computation and Language · Computer Science 2018-11-06 Anthony Bau , Yonatan Belinkov , Hassan Sajjad , Nadir Durrani , Fahim Dalvi , James Glass

Neuron analysis provides insights into how knowledge is structured in representations and discovers the role of neurons in the network. In addition to developing an understanding of our models, neuron analysis enables various applications…

Computation and Language · Computer Science 2023-05-29 Fahim Dalvi , Hassan Sajjad , Nadir Durrani

Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resources. However, what pieces of information are understood in…

Computation and Language · Computer Science 2024-01-31 Shrayani Mondal , Rishabh Garodia , Arbaaz Qureshi , Taesung Lee , Youngja Park

As Natural Language Processing (NLP) models continue to evolve and become integral to high-stakes applications, ensuring their interpretability remains a critical challenge. Given the growing variety of explainability methods and diverse…

Computation and Language · Computer Science 2025-05-05 Mahdi Dhaini , Kafaite Zahra Hussain , Efstratios Zaradoukas , Gjergji Kasneci

Interpretability methods are valuable only if their explanations faithfully describe the explained model. In this work, we consider neural networks whose predictions are invariant under a specific symmetry group. This includes popular…

Machine Learning · Computer Science 2023-10-06 Jonathan Crabbé , Mihaela van der Schaar

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain…

Computation and Language · Computer Science 2022-07-29 Yaozong Shen , Lijie Wang , Ying Chen , Xinyan Xiao , Jing Liu , Hua Wu

The remarkable performance of convolutional neural networks (CNNs) is entangled with their huge number of uninterpretable parameters, which has become the bottleneck limiting the exploitation of their full potential. Towards network…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Yuchao Li , Rongrong Ji , Shaohui Lin , Baochang Zhang , Chenqian Yan , Yongjian Wu , Feiyue Huang , Ling Shao

The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human…

Neurons and Cognition · Quantitative Biology 2020-10-20 Ilya Kuzovkin

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Machine Learning · Computer Science 2022-02-24 Jayneel Parekh , Pavlo Mozharovskyi , Florence d'Alché-Buc

A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component. A common practice for evaluating whether an interpretability method is…

Computation and Language · Computer Science 2023-05-12 Josip Jukić , Martin Tutek , Jan Šnajder

Natural Language Processing prides itself to be an empirically-minded, if not outright empiricist field, and yet lately it seems to get itself into essentialist debates on issues of meaning and measurement ("Do Large Language Models…

Computation and Language · Computer Science 2023-10-30 David Schlangen

It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…

Machine Learning · Computer Science 2022-03-07 Ashkan Khakzar , Pedram Khorsandi , Rozhin Nobahari , Nassir Navab

State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased interest in designing more interpretable deep models for NLP…

Computation and Language · Computer Science 2020-04-27 Jay DeYoung , Sarthak Jain , Nazneen Fatema Rajani , Eric Lehman , Caiming Xiong , Richard Socher , Byron C. Wallace

Neural networks models for NLP are typically implemented without the explicit encoding of language rules and yet they are able to break one performance record after another. This has generated a lot of research interest in interpreting the…

Computation and Language · Computer Science 2019-11-14 Mariya Toneva , Leila Wehbe

Current natural language understanding (NLU) models have been continuously scaling up, both in terms of model size and input context, introducing more hidden and input neurons. While this generally improves performance on average, the extra…

Computation and Language · Computer Science 2024-03-12 Yunchang Zhu , Liang Pang , Kangxi Wu , Yanyan Lan , Huawei Shen , Xueqi Cheng