Related papers: Benchmarking and Enhancing Disentanglement in Conc…

In this work, we introduce InfoDisent, a hybrid approach to explainability based on the information bottleneck principle. InfoDisent enables the disentanglement of information in the final layer of any pretrained model into atomic concepts,…

We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with…

The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other,…

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

Due to the high stakes in medical decision-making, there is a compelling demand for interpretable deep learning methods in medical image analysis. Concept Bottleneck Models (CBM) have emerged as an active interpretable framework…

Accurately assessing student knowledge is central to education. Cognitive Diagnosis (CD) models estimate student proficiency at a fixed point in time, while Knowledge Tracing (KT) methods model evolving knowledge states to predict future…

In this work, we generalize the information bottleneck (IB) approach to the multi-view learning context. The exponentially growing complexity of the optimal representation motivates the development of two novel formulations with more…

The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which is typically implemented by optimizing the IB Lagrangian that…

Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts. Concept learning models, however, have been shown to…

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must identify and address the sources of this variance. Recent…

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in…

Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data…

Recent research has seen significant interest in methods for concept removal and targeted forgetting in text-to-image diffusion models. In this paper, we conduct a comprehensive white-box analysis showing the vulnerabilities in existing…

Despite strong average-case performance, deep learning models often exhibit systematic errors on specific population groups, known as error slices. Identifying these groups and the root causes of their failures is critical for model…

In recent years, Visual Anomaly Detection (VAD) has gained significant attention due to its ability to identify defects using only normal images during training. Many VAD models work without supervision but are still able to provide visual…

Unsupervised image-to-image translation methods have achieved tremendous success in recent years. However, it can be easily observed that their models contain significant entanglement which often hurts the translation performance. In this…

Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that…