English
Related papers

Related papers: An Interpretability Illusion for BERT

200 papers

Many proposed applications of neural networks in machine learning, cognitive/brain science, and society hinge on the feasibility of inner interpretability via circuit discovery. This calls for empirical and theoretical explorations of…

Artificial Intelligence · Computer Science 2025-04-02 Federico Adolfi , Martina G. Vilas , Todd Wareham

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Siyu Zhang

A wide variety of model explanation approaches have been proposed in recent years, all guided by very different rationales and heuristics. In this paper, we take a new route and cast interpretability as a statistical inference problem. We…

Machine Learning · Computer Science 2024-01-01 Hugo Henri Joseph Senetaire , Damien Garreau , Jes Frellsen , Pierre-Alexandre Mattei

We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to context-free or…

Computation and Language · Computer Science 2021-03-19 Leonid Boytsov , Zico Kolter

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…

Artificial Intelligence · Computer Science 2021-08-17 Forough Poursabzi-Sangdeh , Daniel G. Goldstein , Jake M. Hofman , Jennifer Wortman Vaughan , Hanna Wallach

Probabilistic abstract interpretation is a theory used to extract particular properties of a computer program when it is infeasible to test every single inputs. In this paper we apply the theory on neural networks for the same purpose: to…

Artificial Intelligence · Computer Science 2026-03-27 Zhuofan Zhang , Herbert Wiklicky

This work focuses on analyzing the form and extent of syntactic abstraction captured by BERT by extracting labeled dependency trees from self-attentions. Previous work showed that individual BERT heads tend to encode particular dependency…

Computation and Language · Computer Science 2021-01-01 Tomasz Limisiewicz , Rudolf Rosa , David Mareček

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

Machine Learning · Computer Science 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

People ``understand'' the world via vision, hearing, tactile, and also the past experience. Human experience can be learned through normal learning (we call it explicit knowledge), or subconsciously (we call it implicit knowledge). These…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Chien-Yao Wang , I-Hau Yeh , Hong-Yuan Mark Liao

The concept of causal abstraction got recently popularised to demystify the opaque decision-making processes of machine learning models; in short, a neural network can be abstracted as a higher-level algorithm if there exists a function…

Machine Learning · Computer Science 2025-11-13 Denis Sutter , Julian Minder , Thomas Hofmann , Tiago Pimentel

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researchers to study the underlying knowledge encoded by these…

Artificial Intelligence · Computer Science 2021-06-03 Carlos Aspillaga , Marcelo Mendoza , Alvaro Soto

Neural rationale models are popular for interpretable predictions of NLP tasks. In these, a selector extracts segments of the input text, called rationales, and passes these segments to a classifier for prediction. Since the rationale is…

Computation and Language · Computer Science 2022-07-26 Yiming Zheng , Serena Booth , Julie Shah , Yilun Zhou

Understanding neural networks is challenging due to their high-dimensional, interacting components. Inspired by human cognition, which processes complex sensory data by chunking it into recurring entities, we propose leveraging this…

Machine Learning · Computer Science 2025-02-05 Shuchen Wu , Stephan Alaniz , Eric Schulz , Zeynep Akata

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…

Computation and Language · Computer Science 2022-11-04 Gal Patel , Leshem Choshen , Omri Abend

Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems. We demonstrate that the sentence-level representations produced by some off-the-shelf contextualized…

Computation and Language · Computer Science 2022-06-06 Xiliang Zhu , David Rossouw , Shayna Gardiner , Simon Corston-Oliver

Pre-trained contextual language models are ubiquitously employed for language understanding tasks, but are unsuitable for resource-constrained systems. Noncontextual word embeddings are an efficient alternative in these settings. Such…

Computation and Language · Computer Science 2023-04-24 Anik Saha , Alex Gittens , Bulent Yener

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving…

Cryptography and Security · Computer Science 2025-06-24 Marcos Florencio , Thomas Barton