Related papers: SEAT: Stable and Explainable Attention
Recent studies evaluating various criteria for explainable artificial intelligence (XAI) suggest that fidelity, stability, and comprehensibility are among the most important metrics considered by users of AI across a diverse collection of…
Explainable artificial intelligence has been gaining attention in the past few years. However, most existing methods are based on gradients or intermediate features, which are not directly involved in the decision-making process of the…
Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to generate coherent natural language explanations (NLE). The…
We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…
Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers,…
Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…
Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, debugging, and…
Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long…
Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…
Sentiment Analysis has seen much progress in the past two decades. For the past few years, neural network approaches, primarily RNNs and CNNs, have been the most successful for this task. Recently, a new category of neural networks,…
Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, there is a debate on whether attention weights can, in fact,…
Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or…
Neural networks with attention have proven effective for many natural language processing tasks. In this paper, we develop attention mechanisms for uncertainty detection. In particular, we generalize standardly used attention mechanisms by…
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current explanations of this mechanism are mainly based on intuitions…
Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…
Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of…
This paper presents a new method for anomaly detection in automated systems with time and compute sensitive requirements, such as autonomous driving, with unparalleled efficiency. As systems like autonomous driving become increasingly…
Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier's decision. We use this framework to…
There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of…
In this paper we study a rational inattention model in environments where the decision maker faces uncertainty about the true prior distribution over states. The decision maker seeks to select a stochastic choice rule over a finite set of…