This paper introduces the UCFE: User-Centric Financial Expertise benchmark, an innovative framework designed to evaluate the ability of large language models (LLMs) to handle complex real-world financial tasks. UCFE benchmark adopts a hybrid approach that combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios. Firstly, we conducted a user study involving 804 participants, collecting their feedback on financial tasks. Secondly, based on this feedback, we created our dataset that encompasses a wide range of user intents and interactions. This dataset serves as the foundation for benchmarking 12 LLM services using the LLM-as-Judge methodology. Our results show a significant alignment between benchmark scores and human preferences, with a Pearson correlation coefficient of 0.78, confirming the effectiveness of the UCFE dataset and our evaluation approach. UCFE benchmark not only reveals the potential of LLMs in the financial sector but also provides a robust framework for assessing their performance and user satisfaction. The benchmark dataset and evaluation code are available.

Efforts to mitigate bias and enhance fairness in the artificial intelligence (AI) community have predominantly focused on technical solutions. While numerous reviews have addressed bias in AI, this review uniquely focuses on the practical limitations of technical solutions in healthcare settings, providing a structured analysis across five key dimensions affecting their real-world implementation: who defines bias and fairness; which mitigation strategy to use and prioritize among dozens that are inconsistent and incompatible; when in the AI development stages the solutions are most effective; for which populations; and the context in which the solutions are designed. We illustrate each limitation with empirical studies focusing on healthcare and biomedical applications. Moreover, we discuss how value-sensitive AI, a framework derived from technology design, can engage stakeholders and ensure that their values are embodied in bias and fairness mitigation solutions. Finally, we discuss areas that require further investigation and provide practical recommendations to address the limitations covered in the study.

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples. While numerous successful adversarial attacks have been proposed, defenses against these attacks remain relatively understudied. Existing defense approaches either focus on negating the effects of perturbations caused by the attacks to restore the DNNs' original predictions or use a secondary model to detect adversarial examples. However, these methods often become ineffective due to the continuous advancements in attack techniques. We propose a novel universal and lightweight method to detect adversarial examples by analyzing the layer outputs of DNNs. Through theoretical justification and extensive experiments, we demonstrate that our detection method is highly effective, compatible with any DNN architecture, and applicable across different domains, such as image, video, and audio. Goodfellow et al. (2014) demonstrated that deep neural networks (DNNs) are vulnerable to adversarial examples and proposed the Fast Gradient Sign Method (FGSM) to craft these adversarial examples by adding perturbations to the model inputs, leveraging the linear nature of DNNs. After the initial introduction of FGSM, various adversarial attacks were proposed across different domains. However, compared to the vast diversity among attack techniques, existing defense methods are built on a few different strategies.

This essay examines how Artificial Intelligence (AI) systems are becoming more integral to international affairs by affecting how global governors exert power and pursue digital sovereignty. We first introduce a taxonomy of multifaceted AI payoffs for governments and corporations related to instrumental, structural, and discursive power in the domains of violence, markets, and rights. We next leverage different institutional and practice perspectives on sovereignty to assess how digital sovereignty is variously implicated in AI-empowered global governance. States both seek sovereign control over AI infrastructures in the institutional approach, while establishing sovereign competence through AI infrastructures in the practice approach. Overall, we present the digital sovereignty stakes of AI as related to entanglements of public and private power. Rather than foreseeing technology companies as replacing states, we argue that AI systems will embed in global governance to create dueling dynamics of public/private cooperation and contestation. We conclude with sketching future directions for IR research on AI and global governance.

Explainable Artificial Intelligence (AI) focuses on helping humans understand the working of AI systems or their decisions and has been a cornerstone of AI for decades. Recent research in explainability has focused on explaining the workings of AI models or model explainability. There have also been several position statements and review papers detailing the needs of end-users for user-centered explainability but fewer implementations. Hence, this thesis seeks to bridge some gaps between model and user-centered explainability. We create an explanation ontology (EO) to represent literature-derived explanation types via their supporting components. We implement a knowledge-augmented question-answering (QA) pipeline to support contextual explanations in a clinical setting. Finally, we are implementing a system to combine explanations from different AI methods and data modalities. Within the EO, we can represent fifteen different explanation types, and we have tested these representations in six exemplar use cases. We find that knowledge augmentations improve the performance of base large language models in the contextualized QA, and the performance is variable across disease groups. In the same setting, clinicians also indicated that they prefer to see actionability as one of the main foci in explanations. In our explanations combination method, we plan to use similarity metrics to determine the similarity of explanations in a chronic disease detection setting. Overall, through this thesis, we design methods that can support knowledge-enabled explanations across different use cases, accounting for the methods in today's AI era that can generate the supporting components of these explanations and domain knowledge sources that can enhance them.

Attacking fairness is crucial because compromised models can introduce biased outcomes, undermining trust and amplifying inequalities in sensitive applications like hiring, healthcare, and law enforcement. This highlights the urgent need to understand how fairness mechanisms can be exploited and to develop defenses that ensure both fairness and robustness. We introduce BadFair, a novel backdoored fairness attack methodology. BadFair stealthily crafts a model that operates with accuracy and fairness under regular conditions but, when activated by certain triggers, discriminates and produces incorrect results for specific groups. This type of attack is particularly stealthy and dangerous, as it circumvents existing fairness detection methods, maintaining an appearance of fairness in normal use. Our findings reveal that BadFair achieves a more than 85% attack success rate in attacks aimed at target groups on average while only incurring a minimal accuracy loss. Moreover, it consistently exhibits a significant discrimination score, distinguishing between pre-defined target and non-target attacked groups across various datasets and models.

Telephone spam has been among the highest network security concerns for users for many years. In response, industry and government have deployed new technologies and regulations to curb the problem, and academic and industry researchers have provided methods and measurements to characterize robocalls. Have these efforts borne fruit? Are the research characterizations reliable, and have the prevention and deterrence mechanisms succeeded? In this paper, we address these questions through analysis of data from several independently-operated vantage points, ranging from industry and academic voice honeypots to public enforcement and consumer complaints, some with over 5 years of historic data. We first describe how we address the non-trivial methodological challenges of comparing disparate data sources, including comparing audio and transcripts from about 3 million voice calls. We also detail the substantial coherency of these diverse perspectives, which dramatically strengthens the evidence for the conclusions we draw about robocall characterization and mitigation while highlighting advantages of each approach. Among our many findings, we find that unsolicited calls are in slow decline, though complaints and call volumes remain high. We also find that robocallers have managed to adapt to STIR/SHAKEN, a mandatory call authentication scheme. In total, our findings highlight the most promising directions for future efforts to characterize and stop telephone spam.

Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models (SpeechLMs). Earlier SpeechLMs focused on single-turn speech-based question answering (QA), where user input comprised a speech context and a text question. More recent studies have extended this to multi-turn conversations, though they often require complex, multi-stage supervised fine-tuning (SFT) with diverse data. Another critical challenge with SpeechLMs is catastrophic forgetting-where models optimized for speech tasks suffer significant degradation in text-only performance. To mitigate these issues, we propose a novel single-stage joint speech-text SFT approach on the low-rank adaptation (LoRA) of the LLM backbone. Our joint SFT combines text-only SFT data with three types of speech-related data: speech recognition and translation, speech-based QA, and mixed-modal SFT. Compared to previous SpeechLMs with 7B or 13B parameters, our 3B model demonstrates superior performance across various speech benchmarks while preserving the original capabilities on text-only tasks. Furthermore, our model shows emergent abilities of effectively handling previously unseen prompts and tasks, including multi-turn, mixed-modal inputs.

Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated data or predefined task templates to direct powerful LLMs in synthesizing task-relevant data for effective model training. However, this dependence on manually designed components may constrain the scope of generated data, potentially overlooking critical edge cases or novel scenarios that could challenge the model. In this paper, we present a novel approach, ReverseGen, designed to automatically generate effective training samples that expose the weaknesses of LLMs. Specifically, we introduce a dedicated proposer trained to produce queries that lead target models to generate unsatisfactory responses. These failure-inducing queries are then used to construct training data, helping to address the models' shortcomings and improve overall performance. Our approach is flexible and can be applied to models of various scales (3B, 7B, and 8B). We evaluate ReverseGen on three key applications (safety, honesty, and math), demonstrating that our generated data is both highly effective and diverse. Models fine-tuned with ReverseGen-generated data consistently outperform those trained on human-annotated or general model-generated data, offering a new perspective on data synthesis for task-specific LLM enhancement.

We study Federated Causal Inference, an approach to estimate treatment effects from decentralized data across centers. We compare three classes of Average Treatment Effect (ATE) estimators derived from the Plug-in G-Formula, ranging from simple meta-analysis to one-shot and multi-shot federated learning, the latter leveraging the full data to learn the outcome model (albeit requiring more communication). Focusing on Randomized Controlled Trials (RCTs), we derive the asymptotic variance of these estimators for linear models. Our results provide practical guidance on selecting the appropriate estimator for various scenarios, including heterogeneity in sample sizes, covariate distributions, treatment assignment schemes, and center effects. We validate these findings with a simulation study.