相关论文: Being Right for Whose Right Reasons?

Adding explanations to recommender systems is said to have multiple benefits, such as increasing user trust or system transparency. Previous work from other application areas suggests that specific user characteristics impact the users'…

Human explanations of natural language, rationales, form a tool to assess whether models learn a label for the right reasons or rely on dataset-specific shortcuts. Sufficiency is a common metric for estimating the informativeness of…

There is a growing body of work on learning from human feedback to align various aspects of machine learning systems with human values and preferences. We consider the setting of fairness in content moderation, in which human feedback is…

Large Language Models (LLMs) have emerged as powerful support tools across various natural language tasks and a range of application domains. Recent studies focus on exploring their capabilities for data annotation. This paper provides a…

Counterfactual explanations are a widely used approach in Explainable AI, offering actionable insights into decision-making by illustrating how small changes to input data can lead to different outcomes. Despite their importance, evaluating…

Conformal prediction is a model-agnostic approach to generating prediction sets that cover the true class with a high probability. Although its prediction set size is expected to capture aleatoric uncertainty, there is a lack of evidence…

Majority voting and averaging are common approaches employed to resolve annotator disagreements and derive single ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often…

Automatic content moderation is crucial to ensuring safety in social media. Language Model-based classifiers are being increasingly adopted for this task, but it has been shown that they perpetuate racial and social biases. Even if several…

Explainability is key to enhancing artificial intelligence's trustworthiness in medicine. However, several issues remain concerning the actual benefit of explainable models for clinical decision-making. Firstly, there is a lack of consensus…

Explainable AI provides insight into the "why" for model predictions, offering potential for users to better understand and trust a model, and to recognize and correct AI predictions that are incorrect. Prior research on human and…

Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts…

Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking…

The advanced reasoning capabilities of Large Reasoning Models enable them to thoroughly understand and apply safety policies through deliberate thought processes, thereby improving the models' safety. Beyond safety, these models must also…

Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be…

Explainability is needed to establish confidence in machine learning results. Some explainable methods take a post hoc approach to explain the weights of machine learning models, others highlight areas of the input contributing to…

Instead of using a single ground truth for language processing tasks, several recent studies have examined how to represent and predict the labels of the set of annotators. However, often little or no information about annotators is known,…

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

The challenge of creating interpretable models has been taken up by two main research communities: ML researchers primarily focused on lower-level explainability methods that suit the needs of engineers, and HCI researchers who have more…

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a…