English
Related papers

Related papers: An Interpretability Illusion for BERT

200 papers

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

Machine Learning · Computer Science 2022-04-05 Pedro Sandoval-Segura , Wallace Lawson

Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors,…

Machine Learning · Statistics 2016-03-30 Seyed Mostafa Kia

Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art…

Computation and Language · Computer Science 2020-06-02 Bin Wang , C. -C. Jay Kuo

Does the effectiveness of neural language models derive entirely from accurate modeling of surface word co-occurrence statistics, or do these models represent and reason about the world they describe? In BART and T5 transformer language…

Computation and Language · Computer Science 2021-06-03 Belinda Z. Li , Maxwell Nye , Jacob Andreas

In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process…

Machine Learning · Statistics 2025-10-22 Gianluigi Lopardo , Frederic Precioso , Damien Garreau

In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is…

Machine Learning · Computer Science 2019-10-14 Maximilian Idahl , Megha Khosla , Avishek Anand

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…

Computation and Language · Computer Science 2019-05-28 Jacob Devlin , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

Fake news detection has become a major task to solve as there has been an increasing number of fake news on the internet in recent years. Although many classification models have been proposed based on statistical learning methods showing…

Computation and Language · Computer Science 2022-07-26 Daesoo Lee

It has been reliably shown that the similarity of word embeddings obtained from popular neural models such as BERT approximates effectively a form of semantic similarity of the meaning of those words. It is therefore natural to wonder if…

Artificial Intelligence · Computer Science 2024-08-02 Mathieu d'Aquin , Emmanuel Nauer

High quality explanations of neural networks (NNs) should exhibit two key properties. Completeness ensures that they accurately reflect a network's function and interpretability makes them understandable to humans. Many existing methods…

Machine Learning · Computer Science 2025-03-20 Nolan Dey , Eric Taylor , Alexander Wong , Bryan Tripp , Graham W. Taylor

Machine learning has shown much promise in helping improve the quality of medical, legal, and financial decision-making. In these applications, machine learning models must satisfy two important criteria: (i) they must be causal, since the…

Machine Learning · Computer Science 2021-10-12 Carolyn Kim , Osbert Bastani

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez

Interpretability is an important aspect of the trustworthiness of a model's predictions. Transformer's predictions are widely explained by the attention weights, i.e., a probability distribution generated at its self-attention unit (head).…

Computation and Language · Computer Science 2021-06-03 Rishabh Bhardwaj , Navonil Majumder , Soujanya Poria , Eduard Hovy

Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference.…

Computation and Language · Computer Science 2021-08-04 Amit Gajbhiye , Noura Al Moubayed , Steven Bradley

Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or…

Machine Learning · Computer Science 2019-03-18 Riccardo Guidotti , Salvatore Ruggieri

Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method to interpret arbitrary samples from a word vector space. To…

Computation and Language · Computer Science 2019-04-03 Robert Schwarzenberg , Lisa Raithel , David Harbecke

We use the English model of BERT and explore how a deletion of one word in a sentence changes representations of other words. Our hypothesis is that removing a reducible word (e.g. an adjective) does not affect the representation of other…

Computation and Language · Computer Science 2019-06-28 Rudolf Rosa , David Mareček

BERT, as one of the pretrianed language models, attracts the most attention in recent years for creating new benchmarks across GLUE tasks via fine-tuning. One pressing issue is to open up the blackbox and explain the decision makings of…

Computation and Language · Computer Science 2021-01-05 Zhengxuan Wu , Desmond C. Ong

While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large foundation models are far from interpretable, understanding…

Machine Learning · Computer Science 2026-02-24 Shingo Kodama , Niv Cohen , Micah Adler , Nir Shavit

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for…

Computation and Language · Computer Science 2020-10-12 Xiangpeng Wei , Heng Yu , Yue Hu , Rongxiang Weng , Luxi Xing , Weihua Luo