相关论文: Are Recommenders Self-Aware? Label-Free Recommenda…

Though it has been recognized that recommending serendipitous (i.e., surprising and relevant) items can be helpful for increasing users' satisfaction and behavioral intention, how to measure serendipity in the offline environment is still…

Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work explores various forms of reward shaping and step-level…

Deep Learning sets the state-of-the-art in many challenging tasks showing outstanding performance in a broad range of applications. Despite its success, it still lacks robustness hindering its adoption in medical applications. Modeling…

With the rise of increasingly powerful and user-facing NLP systems, there is growing interest in assessing whether they have a good representation of uncertainty by evaluating the quality of their predictive distribution over outcomes. We…

Models that top leaderboards often perform unsatisfactorily when deployed in real world applications; this has necessitated rigorous and expensive pre-deployment model testing. A hitherto unexplored facet of model performance is: Are our…

Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, it does not fulfill the closed world assumption of…

When constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide labels of inconsistent quality due to their varying…

The capability to detect objects is a core part of autonomous driving. Due to sensor noise and incomplete data, perfectly detecting and localizing every object is infeasible. Therefore, it is important for a detector to provide the amount…

Clinical dataset labels are rarely certain as annotators disagree and confidence is not uniform across cases. Typical aggregation procedures, such as majority voting, obscure this variability. In simple experiments on medical imaging…

Current practice for evaluating recommender systems typically focuses on point estimates of user-oriented effectiveness metrics or business metrics, sometimes combined with additional metrics for considerations such as diversity and…

In a broad range of classification and decision making problems, one is given the advice or predictions of several classifiers, of unknown reliability, over multiple questions or queries. This scenario is different from the standard…

Users want to know the reliability of the recommendations; they do not accept high predictions if there is no reliability evidence. Recommender systems should provide reliability values associated with the predictions. Research into…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…

Recommender systems are information retrieval methods that predict user preferences to personalize services. These systems use the feedback and the ratings provided by users to model the behavior of users and to generate recommendations.…

Most recent paradigms of generative model-based recommendation still face challenges related to the cold-start problem. Existing models addressing cold item recommendations mainly focus on acquiring more knowledge to enrich embeddings or…

This paper explores generalised probabilistic modelling and uncertainty estimation in comparative LLM-as-a-judge frameworks. We show that existing Product-of-Experts methods are specific cases of a broader framework, enabling diverse…

Machine learning systems can help humans to make decisions by providing decision suggestions (i.e., a label for a datapoint). However, individual datapoints do not always provide enough clear evidence to make confident suggestions. Although…

Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The…

Learning user preferences for products based on their past purchases or reviews is at the cornerstone of modern recommendation engines. One complication in this learning task is that some users are more likely to purchase products or review…

Current person image retrieval methods have achieved great improvements in accuracy metrics. However, they rarely describe the reliability of the prediction. In this paper, we propose an Uncertainty-Aware Learning (UAL) method to remedy…