Related papers: MIB: A Mechanistic Interpretability Benchmark

We introduce a novel and interpretable path-based music similarity measure. Our similarity measure assumes that items, such as songs and artists, and information about those items are represented in a knowledge graph. We find paths in the…

As machine learning models are increasingly deployed in high-stakes domains, the need for interpretability has grown to meet strict regulatory and accountability constraints. Despite this interest, systematic evaluations of inherently…

Multiple imputation (MI) is a popular approach for dealing with missing data arising from non-response in sample surveys. Multiple imputation by chained equations (MICE) is one of the most widely used MI algorithms for multivariate data,…

Interpretability techniques aim to provide the rationale behind a model's decision, typically by explaining either an individual prediction (local explanation, e.g. 'why is this patient diagnosed with this condition') or a class of…

Motor Imagery-Based Brain-Computer Interfaces (MI-BCIs) are systems that detect and interpret brain activity patterns linked to the mental visualization of movement, and then translate these into instructions for controlling external…

The black box nature of deep neural networks poses a significant challenge for the deployment of transparent and trustworthy artificial intelligence (AI) systems. With the growing presence of AI in society, it becomes increasingly important…

Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models. Existing automated circuit discovery work applies activation…

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a…

Variational mutual information (MI) estimators are widely used in unsupervised representation learning methods such as contrastive predictive coding (CPC). A lower bound on MI can be obtained from a multi-class classification problem, where…

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

Mechanistic interpretability methods aim to identify the algorithm a neural network implements, but it is difficult to validate such methods when the true algorithm is unknown. This work presents InterpBench, a collection of semi-synthetic…

Although media bias detection is a complex multi-task problem, there is, to date, no unified benchmark grouping these evaluation tasks. We introduce the Media Bias Identification Benchmark (MBIB), a comprehensive benchmark that groups…

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…

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…

Human Multimodal Language Understanding (MLU) aims to infer human intentions by integrating related cues from heterogeneous modalities. Existing works predominantly follow a ``learning to attend" paradigm, which maximizes mutual information…

Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences…

The interventional effects approach to causal mediation analysis is increasingly common in epidemiologic research, given its potential to address policy-relevant questions about hypothetical mediator interventions. Multiple imputation (MI)…

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…