Related papers: TaylorPODA: A Taylor Expansion-Based Method to Imp…

In this paper we introduce the idea of improving the performance of parametric temporal-difference (TD) learning algorithms by selectively emphasizing or de-emphasizing their updates on different time steps. In particular, we show that…

Many applications of data-driven models demand transparency of decisions, especially in health care, criminal justice, and other high-stakes environments. Modern trends in machine learning research have led to algorithms that are…

Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model's reasoning, they may not align with human intuition, making the explanations not…

While pre-trained large-scale deep models have garnered attention as an important topic for many downstream natural language processing (NLP) tasks, such models often make unreliable predictions on out-of-distribution (OOD) inputs. As such,…

While research on applications and evaluations of explanation methods continues to expand, fairness of the explanation methods concerning disparities in their performance across subgroups remains an often overlooked aspect. In this paper,…

Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-box prompting alone can recover the…

Several proposals have been put forward in recent years for improving out-of-distribution (OOD) performance through mitigating dataset biases. A popular workaround is to train a robust model by re-weighting training examples based on a…

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring…

In recent years, training data attribution (TDA) methods have emerged as a promising direction for the interpretability of neural networks. While research around TDA is thriving, limited effort has been dedicated to the evaluation of…

Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it…

For AI systems to garner widespread public acceptance, we must develop methods capable of explaining the decisions of black-box models such as neural networks. In this work, we identify two issues of current explanatory methods. First, we…

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian information-theoretic problem: subsets are scored by the…

We introduce $\textit{Backward Conformal Prediction}$, a method that guarantees conformal coverage while providing flexible control over the size of prediction sets. Unlike standard conformal prediction, which fixes the coverage level and…

Deep learning provides a new avenue for image restoration, which demands a delicate balance between fine-grained details and high-level contextualized information during recovering the latent clear image. In practice, however, existing…

Many training data attribution (TDA) methods aim to estimate how a model's behavior would change if one or more data points were removed from the training set. Methods based on implicit differentiation, such as influence functions, can be…

This document is a guide to the implementation of true online emphatic TD($\lambda$), a model-free temporal-difference algorithm for learning to make long-term predictions which combines the emphasis idea (Sutton, Mahmood & White 2015) and…

Training data attribution (TDA) methods aim to measure how training data impacts a model's predictions. While gradient-based attribution methods, such as influence functions, offer theoretical grounding, their computational costs make them…

Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map…

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…