We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our architecture offers three key benefits: i) Control: We can intervene on concept values to precisely control the properties of generated proteins, achieving a 3$\times$ larger change in desired concept values compared to baselines. ii) Interpretability: A linear mapping between concept values and predicted tokens allows transparent analysis of the model's decision-making process. iii) Debugging: This transparency facilitates easy debugging of trained models. Our models achieve pre-training perplexity and downstream task performance comparable to traditional masked protein language models, demonstrating that interpretability does not compromise performance. While adaptable to any language model, we focus on masked protein language models due to their importance in drug discovery and the ability to validate our model's capabilities through real-world experiments and expert knowledge. We scale our CB-pLM from 24 million to 3 billion parameters, making them the largest Concept Bottleneck Models trained and the first capable of generative language modeling.

We introduce a generative model with an intrinsically interpretable layer---a concept bottleneck layer---that constrains the model to encode human-understandable concepts. The concept bottleneck layer partitions the generative model into three parts: the pre-concept bottleneck portion, the CB layer, and the post-concept bottleneck portion. To train CB generative models, we complement the traditional task-based loss function for training generative models with a concept loss and an orthogonality loss. The CB layer and these loss terms are model agnostic, which we demonstrate by applying the CB layer to three different families of generative models: generative adversarial networks, variational autoencoders, and diffusion models. On multiple datasets across different types of generative models, steering a generative model, with the CB layer, outperforms all baselines---in some cases, it is \textit{10 times} more effective. In addition, we show how the CB layer can be used to interpret the output of the generative model and debug the model during or post training.

We present a method for identifying groups of test examples---slices---on which a model under-performs, a task now known as slice discovery. We formalize coherence---a requirement that erroneous predictions, within a slice, should be wrong for the same reason---as a key property that any slice discovery method should satisfy. We then use influence functions to derive a new slice discovery method, InfEmbed, which satisfies coherence by returning slices whose examples are influenced similarly by the training data. InfEmbed is simple, and consists of applying K-Means clustering to a novel representation we deem influence embeddings. We show InfEmbed outperforms current state-of-the-art methods on 2 benchmarks, and is effective for model debugging across several case studies.

We investigate whether post-hoc model explanations are effective for diagnosing model errors--model debugging. In response to the challenge of explaining a model's prediction, a vast array of explanation methods have been proposed. Despite increasing use, it is unclear if they are effective. To start, we categorize \textit{bugs}, based on their source, into: ~\textit{data, model, and test-time} contamination bugs. For several explanation methods, we assess their ability to: detect spurious correlation artifacts (data contamination), diagnose mislabeled training examples (data contamination), differentiate between a (partially) re-initialized model and a trained one (model contamination), and detect out-of-distribution inputs (test-time contamination). We find that the methods tested are able to diagnose a spurious background bug, but not conclusively identify mislabeled training examples. In addition, a class of methods, that modify the back-propagation algorithm are invariant to the higher layer parameters of a deep network; hence, ineffective for diagnosing model contamination. We complement our analysis with a human subject study, and find that subjects fail to identify defective models using attributions, but instead rely, primarily, on model predictions. Taken together, our results provide guidance for practitioners and researchers turning to explanations as tools for model debugging.

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actionable methodology to evaluate what kinds of explanations a given method can and cannot provide. We find that reliance, solely, on visual assessment can be misleading. Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process. Consequently, methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model, such as, finding outliers in the data, explaining the relationship between inputs and outputs that the model learned, and debugging the model. We interpret our findings through an analogy with edge detection in images, a technique that requires neither training data nor model. Theory in the case of a linear model and a single-layer convolutional neural network supports our experimental findings.

We present a transformation procedure for large scale individual level data that produces output data in which no linear combinations of the resulting attributes can yield the original sensitive attributes from the transformed data. In doing this, our procedure eliminates all linear information regarding a sensitive attribute from the input data. The algorithm combines principal components analysis of the data set with orthogonal projection onto the subspace containing the sensitive attribute(s). The algorithm presented is motivated by applications where there is a need to drastically `sanitize' a data set of all information relating to sensitive attribute(s) before analysis of the data using a data mining algorithm. Sensitive attribute removal (sanitization) is often needed to prevent disparate impact and discrimination on the basis of race, gender, and sexual orientation in high stakes contexts such as determination of access to loans, credit, employment, and insurance. We show through experiments that our proposed algorithm outperforms other privacy preserving techniques by more than 20 percent in lowering the ability to reconstruct sensitive attributes from large scale data.