Motivated by the need to audit complex and black box models, there has been extensiveresearch onquantifying howdatafeatures influence model predictions.

Prompt optimization automatically refines prompting expressions, unlocking the full potential of LLMs in downstream tasks. However, current prompt optimization methods are costly to train and lack sufficient interpretability. This paper proposes enhancing LLMs' reasoning performance by eliciting their causal inference ability from prompting instructions to correct answers. Specifically, we introduce the Self-Causal Instruction Enhancement (SCIE) method, which enables LLMs to generate high-quality, low-quantity observational data, then estimates the causal effect based on these data, and ultimately generates instructions with the optimized causal effect. In SCIE, the instructions are treated as the treatment, and textual features are used to process natural language, establishing causal relationships through treatments between instructions and downstream tasks. Additionally, we propose applying Object-Relational (OR) principles, where the uncovered causal relationships are treated as the inheritable class across task objects, ensuring low-cost reusability. Extensive experiments demonstrate that our method effectively generates instructions that enhance reasoning performance with reduced training cost of prompts, leveraging interpretable textual features to provide actionable insights.

Humor is a fundamental aspect of human communication and cognition, as it plays a crucial role in social engagement. Although theories about humor have evolved over centuries, there is still no agreement on a single, comprehensive humor theory. Likewise, computationally recognizing humor remains a significant challenge despite recent advances in large language models. Moreover, most computational approaches to detecting humor are not based on existing humor theories. This paper contributes to bridging this long-standing gap between humor theory research and computational humor detection by creating an interpretable framework for humor classification, grounded in multiple humor theories, called THInC (Theory-driven Humor Interpretation and Classification). THInC ensembles interpretable GA2M classifiers, each representing a different humor theory. We engineered a transparent flow to actively create proxy features that quantitatively reflect different aspects of theories. An implementation of this framework achieves an F1 score of 0.85. The associative interpretability of the framework enables analysis of proxy efficacy, alignment of joke features with theories, and identification of globally contributing features. This paper marks a pioneering effort in creating a humor detection framework that is informed by diverse humor theories and offers a foundation for future advancements in theory-driven humor classification. It also serves as a first step in automatically comparing humor theories in a quantitative manner.

Fairness-aware classification models have gained increasing attention in recent years as concerns grow on discrimination against some demographic groups. Most existing models require full knowledge of the sensitive features, which can be impractical due to privacy, legal issues, and an individual's fear of discrimination. The key challenge we will address is the group dependency of the unavailability, e.g., people of some age range may be more reluctant to reveal their age. Our solution augments general fairness risks with probabilistic imputations of the sensitive features, while jointly learning the group-conditionally missing probabilities in a variational auto-encoder. Our model is demonstrated effective on both image and tabular datasets, achieving an improved balance between accuracy and fairness.

Research in XAI aims to improve fairness in human-AI decision-making by providing insights into model predictions, and thereby allowing humans to understand and correct for model biases. On the other hand, in the context of human-AI decision-making, previous work has noted that humans often over-rely on AI predictions, and explanations can exacerbate this concern [9]. This is especially troubling if the underlying model contains systematic biases, which may go unnoticed even when teamed with a human. In order for the human-AI team to be successful, the human needs to be able to determine when to rely on or override potentially biased AI predictions. Previous work has shown that explanations can help human-AI teams alleviate model biases when those biases depend directly on protected attributes [18, 54], but little is known in the very common case that protected attributes are not explicitly included, and rather the features used for prediction contain proxies thereof (e.g., zip code for race, length of credit for age, and university attended for gender). In particular, it may be difficult for humans to identify and resolve biased model predictions based on the proxy features present in real-world data, even when explanations are provided. In this work, we study whether explanations can help people to identify model biases and to calibrate their reliance on an AI model based on these biases. We extend this line of investigation beyond direct biases that are revealed through the use of protected (i.e., sensitive) features by considering the effect of explanations when indirect bias is revealed Both co-first authors contributed equally to this manuscript, and each has the right to list their name first on their CV.

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm's decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can persist in discrimination. Indeed, when sensitive features are omitted (fairness under unawareness), they could be inferred through non-linear relations with the so called proxy features. In this work, we propose a way to reveal the potential hidden bias of a machine learning model that can persist even when sensitive features are discarded. This study shows that it is possible to unveil whether the black-box predictor is still biased by exploiting counterfactual reasoning. In detail, when the predictor provides a negative classification outcome, our approach first builds counterfactual examples for a discriminated user category to obtain a positive outcome. Then, the same counterfactual samples feed an external classifier (that targets a sensitive feature) that reveals whether the modifications to the user characteristics needed for a positive outcome moved the individual to the non-discriminated group. When this occurs, it could be a warning sign for discriminatory behavior in the decision process. Furthermore, we leverage the deviation of counterfactuals from the original sample to determine which features are proxies of specific sensitive information. Our experiments show that, even if the model is trained without sensitive features, it often suffers discriminatory biases.

Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice. Existing work tackles this issue by minimizing information about social attributes in models for debiasing. However, the high correlation between target task and social attributes makes bias mitigation incompatible with target task accuracy. Recalling that model bias arises because the learning of features in regard to bias attributes (i.e., bias features) helps target task optimization, we explore the following research question: \emph{Can we leverage proxy features to replace the role of bias feature in target task optimization for debiasing?} To this end, we propose \emph{Proxy Debiasing}, to first transfer the target task's learning of bias information from bias features to artificial proxy features, and then employ causal intervention to eliminate proxy features in inference. The key idea of \emph{Proxy Debiasing} is to design controllable proxy features to on one hand replace bias features in contributing to target task during the training stage, and on the other hand easily to be removed by intervention during the inference stage. This guarantees the elimination of bias features without affecting the target information, thus addressing the fairness-accuracy paradox in previous debiasing solutions. We apply \emph{Proxy Debiasing} to several benchmark datasets, and achieve significant improvements over the state-of-the-art debiasing methods in both of accuracy and fairness.

Accurately forecasting patient arrivals at Urgent Care Clinics (UCCs) and Emergency Departments (EDs) is important for effective resourcing and patient care. However, correctly estimating patient flows is not straightforward since it depends on many drivers. The predictability of patient arrivals has recently been further complicated by the COVID-19 pandemic conditions and the resulting lockdowns. This study investigates how a suite of novel quasi-real-time variables like Google search terms, pedestrian traffic, the prevailing incidence levels of influenza, as well as the COVID-19 Alert Level indicators can both generally improve the forecasting models of patient flows and effectively adapt the models to the unfolding disruptions of pandemic conditions. This research also uniquely contributes to the body of work in this domain by employing tools from the eXplainable AI field to investigate more deeply the internal mechanics of the models than has previously been done. The Voting ensemble-based method combining machine learning and statistical techniques was the most reliable in our experiments. Our study showed that the prevailing COVID-19 Alert Level feature together with Google search terms and pedestrian traffic were effective at producing generalisable forecasts. The implications of this study are that proxy variables can effectively augment standard autoregressive features to ensure accurate forecasting of patient flows. The experiments showed that the proposed features are potentially effective model inputs for preserving forecast accuracies in the event of future pandemic outbreaks.