相关论文: RelatIF: Identifying Explanatory Training Examples…

Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic incentives to manipulate…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward. This is limiting in applications where we are concerned with not only the expected performance, but also the distribution…

Mixed-effect models are flexible tools for researchers in a myriad of fields, but that flexibility comes at the cost of complexity and if users are not careful in how their model is specified, they could be making faulty inferences from…

Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…

Recent developments in large pre-trained language models have enabled unprecedented performance on a variety of downstream tasks. Achieving best performance with these models often leverages in-context learning, where a model performs a…

Imitation learning (IL) is a framework that learns to imitate expert behavior from demonstrations. Recently, IL shows promising results on high dimensional and control tasks. However, IL typically suffers from sample inefficiency in terms…

Meta-learning enables models to rapidly adapt to new tasks by leveraging prior experience, but its adaptation mechanisms remain opaque, especially regarding how past training tasks influence future predictions. We introduce TLXML…

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

The shortcomings of maximum likelihood estimation in the context of model-based reinforcement learning have been highlighted by an increasing number of papers. When the model class is misspecified or has a limited representational capacity,…

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue…

Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in…

While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior. It is well known that, in…

Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and…

Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works have proposed various metrics and algorithms to calculate…

To enhance the interpretability of Reinforcement Learning (RL), we propose Revealing Evolutionary Action Consequence Trajectories (REACT). In contrast to the prevalent practice of validating RL models based on their optimal behavior learned…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

In-context learning (ICL) is a powerful paradigm emerged from large language models (LLMs). Despite its promises, ICL performance is known to be highly sensitive to input examples. In this work, we use $\textit{in-context influences}$ to…

Machine learning models achieve state-of-the-art performance across domains, yet their lack of interpretability limits safe deployment in high-stakes settings. Counterfactual explanations are widely used to provide actionable "what-if"…