Related papers: Causal interpretation rules for encoding and decod…

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

A standard assumption for causal inference from observational data is that one has measured a sufficiently rich set of covariates to ensure that within covariate strata, subjects are exchangeable across observed treatment values. Skepticism…

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing…

In a recent article, Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette's conceptual analysis mischaracterizes the structure of causal claims in coding and other…

Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge. Here, we apply causal intervention techniques to recent transformer models to…

Multilingual language models achieve strong aggregate performance yet often behave unpredictably across languages, scripts, and cultures. We argue that mechanistic explanations for such models should satisfy a \emph{causal} standard: claims…

Decoding human visual neural representations is a challenging task with great scientific significance in revealing vision-processing mechanisms and developing brain-like intelligent machines. Most existing methods are difficult to…

Causal reasoning is a cornerstone of how humans interpret the world. To model and reason about causality, causal graphs offer a concise yet effective solution. Given the impressive advancements in language models, a crucial question arises:…

Decoding EEG during motor imagery is pivotal for the Brain-Computer Interface (BCI) system, influencing its overall performance significantly. As end-to-end data-driven learning methods advance, the challenge lies in balancing model…

Causal models, also known as Structural Equation Models (SEM), are a well-known formalism for representing and reasoning about causal dependencies between events. In this paper, we show that Temporal SEMs (TSEMs), which extend SEMs to…

Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs remains poorly understood. In particular, causal scores produced by regularized neural…

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain…

Language models are traditionally designed around causal masking. In domains with spatial or relational structure, causal masking is often viewed as inappropriate, and sequential linearizations are instead used. Yet the question of whether…

Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. A field-wide goal is to achieve…

Causal Models are like Dependency Graphs and Belief Nets in that they provide a structure and a set of assumptions from which a joint distribution can, in principle, be computed. Unlike Dependency Graphs, Causal Models are models of…

Deep learning has revolutionized the field of artificial intelligence. Based on the statistical correlations uncovered by deep learning-based methods, computer vision has contributed to tremendous growth in areas like autonomous driving and…

Although deep learning techniques show promising results for many neuroimaging tasks in research settings, they have not yet found widespread use in clinical scenarios. One of the reasons for this problem is that many machine learning…

In this paper, we aim to explain the decisions of neural networks by utilizing multimodal information. That is counter-intuitive attributes and counter visual examples which appear when perturbed samples are introduced. Different from…

The field of neuro-symbolic AI aims to benefit from the combination of neural networks and symbolic systems. A cornerstone of the field is the translation or encoding of symbolic knowledge into neural networks. Although many neuro-symbolic…

There has been a substantial amount of research on the relationship between hippocampal neurogenesis and behaviour over the past fifteen years, but the causal role that new neurons have on cognitive and affective behavioural tasks is still…