English
Related papers

Related papers: An Interpretability Illusion for BERT

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

Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A variety of previous works have tried to lift the veil of…

Computation and Language · Computer Science 2021-02-16 Wei-Tsung Kao , Tsung-Han Wu , Po-Han Chi , Chun-Cheng Hsieh , Hung-Yi Lee

How to aggregate information from multiple instances is a key question multiple instance learning. Prior neural models implement different variants of the well-known encoder-decoder strategy according to which all input features are encoded…

Machine Learning · Computer Science 2022-07-26 Markus Zopf

Methods for understanding the decisions of and mechanisms underlying deep neural networks (DNNs) typically rely on building intuition by emphasizing sensory or semantic features of individual examples. For instance, methods aim to visualize…

Computers and Society · Computer Science 2020-10-26 Matthew L. Leavitt , Ari Morcos

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because…

Machine Learning · Computer Science 2025-05-05 Kola Ayonrinde , Louis Jaburi

Hallucination, one kind of pathological translations that bothers Neural Machine Translation, has recently drawn much attention. In simple terms, hallucinated translations are fluent sentences but barely related to source inputs. Arguably,…

Computation and Language · Computer Science 2022-06-28 Jianhao Yan , Fandong Meng , Jie Zhou

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

Machine Learning · Computer Science 2019-08-06 Dylan Slack , Sorelle A. Friedler , Carlos Scheidegger , Chitradeep Dutta Roy

Sparse attention has been claimed to increase model interpretability under the assumption that it highlights influential inputs. Yet the attention distribution is typically over representations internal to the model rather than the inputs…

Computation and Language · Computer Science 2021-06-09 Clara Meister , Stefan Lazov , Isabelle Augenstein , Ryan Cotterell

We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. Sentence-level…

Computation and Language · Computer Science 2019-10-25 Xiaofei Ma , Zhiguo Wang , Patrick Ng , Ramesh Nallapati , Bing Xiang

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a principled notion of interpretability to formally compare…

Artificial Intelligence · Computer Science 2020-11-16 Pablo Barceló , Mikaël Monet , Jorge Pérez , Bernardo Subercaseaux

Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of…

Machine Learning · Statistics 2017-12-08 Fabian Offert

Decision-making in complex systems often relies on machine learning models, yet highly accurate models such as XGBoost and neural networks can obscure the reasoning behind their predictions. In operations research applications,…

Machine Learning · Computer Science 2025-02-28 Gaurav Arwade , Sigurdur Olafsson

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…

Artificial Intelligence · Computer Science 2021-09-21 David Alvarez-Melis , Harmanpreet Kaur , Hal Daumé , Hanna Wallach , Jennifer Wortman Vaughan

Humans possess the capability to reason at an abstract level and to structure information into abstract categories, but the underlying neural processes have remained unknown. Experimental evidence has recently emerged for the organization…

Neurons and Cognition · Quantitative Biology 2022-04-05 Michael G. Müller , Christos H. Papadimitriou , Wolfgang Maass , Robert Legenstein

The success of neural networks builds to a large extent on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these…

Artificial Intelligence · Computer Science 2023-01-03 Lars Holmberg , Paul Davidsson , Per Linde

Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…

Computation and Language · Computer Science 2021-04-08 Hassan S. Shavarani , Anoop Sarkar

Neural language models exhibit impressive performance on a variety of tasks, but their internal reasoning may be difficult to understand. Prior art aims to uncover meaningful properties within model representations via probes, but it is…

Computation and Language · Computer Science 2021-09-21 Mycal Tucker , Peng Qian , Roger Levy

BERT and its variants have achieved state-of-the-art performance in various NLP tasks. Since then, various works have been proposed to analyze the linguistic information being captured in BERT. However, the current works do not provide an…

Computation and Language · Computer Science 2020-10-20 Sahana Ramnath , Preksha Nema , Deep Sahni , Mitesh M. Khapra

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

Machine Learning · Computer Science 2022-07-18 Xuhong Li , Haoyi Xiong , Xingjian Li , Xuanyu Wu , Xiao Zhang , Ji Liu , Jiang Bian , Dejing Dou

One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…

Computation and Language · Computer Science 2019-12-02 Zied Bouraoui , Jose Camacho-Collados , Steven Schockaert