Jimmy Kimmel's big TV comeback strangled as SEVENTY ABC affiliates refuse to air tonight's show Wall Street delivers clear verdict on Trump's Tylenol claims I was a devout Catholic... until I died. I'm the doctor on the cusp of an autism breakthrough... we're using an everyday $2.50 pill to reverse children's symptoms Secret Service foils'espionage' plot in NYC ahead of UN General Assembly that could have crashed Big Apple's phone network The'marry me' sex move that'll make even the most commitment-phobic of men beg to see you again... and it worked for THREE of my friends Sarah Ferguson sent Jeffrey Epstein fawning apology email'after he threatened to destroy her' in'Hannibal Lector-like' phone call The six hidden messages in the texts between Charlie Kirk's'assassin' and his trans lover DECODED Awkward moment Emmanuel Macron rings Trump for help after his motorcade is stopped by cops in New York... but ends up having to get out and walk Kate Middleton delivers a'mic drop' moment in dazzling gold dress identical to the late monarch - giving a glimpse of the Queen she plans to be William is urging his father to disown Fergie and Andrew over Epstein scandal... but King fears they could go rogue and values their loyalty Insiders speak out on Barack and Michelle Obama's secretive yacht vacation amid's**t show': 'They NEEDED this trip' In 2019, gravitational wave detectors on Earth picked up a signal that left scientists baffled. Gravitational waves are ripples in the fabric of space and time, usually created when massive, dense objects like black holes collide. But at less than a tenth of a second long, this sudden burst was far shorter than the drawn-out chirps normally produced by merging black holes. Now, researchers think this strange signal, dubbed GW190521, could have arrived from a parallel universe.

Drone attack kills eight children in Haiti's capital NewsFeed Drone attack kills eight children in Haiti's capital At least 11 people, including eight children, were reported killed in a drone attack in a gang-controlled area of Haiti's capital Port-au-Prince. Relatives of the victims said police were targeting a suspected gang leader. Video: Parents carry children's bodies after Israeli attack on Gaza City Protesters outside UN say recognising Palestine isn't enough

Assessing fairness in artificial intelligence (AI) typically involves AI experts who select protected features, fairness metrics, and set fairness thresholds. However, little is known about how stakeholders, particularly those affected by AI outcomes but lacking AI expertise, assess fairness. To address this gap, we conducted a qualitative study with 30 stakeholders without AI expertise, representing potential decision subjects in a credit rating scenario, to examine how they assess fairness when placed in the role of deciding on features with priority, metrics, and thresholds. We reveal that stakeholders' fairness decisions are more complex than typical AI expert practices: they considered features far beyond legally protected features, tailored metrics for specific contexts, set diverse yet stricter fairness thresholds, and even preferred designing customized fairness. Our results extend the understanding of how stakeholders can meaningfully contribute to AI fairness governance and mitigation, underscoring the importance of incorporating stakeholders' nuanced fairness judgments.

As machine learning models become increasingly embedded in decision-making systems, the ability to "unlearn" targeted data or features is crucial for enhancing model adaptability, fairness, and privacy in models which involves expensive training. To effectively guide machine unlearning, a thorough testing is essential. Existing methods for verification of machine unlearning provide limited insights, often failing in scenarios where the influence is indirect. In this work, we propose CAFÉ, a new causality based framework that unifies datapoint- and feature-level unlearning for verification of black-box ML models. CAFÉ evaluates both direct and indirect effects of unlearning targets through causal dependencies, providing actionable insights with fine-grained analysis. Our evaluation across five datasets and three model architectures demonstrates that CAFÉ successfully detects residual influence missed by baselines while maintaining computational efficiency.

Large Language Models (LLMs) are increasingly deployed in socially complex, interaction-driven tasks, yet their ability to mirror human behavior in emotionally and strategically complex contexts remains underexplored. This study assesses the behavioral alignment of personality-prompted LLMs in adversarial dispute resolution by simulating multi-turn conflict dialogues that incorporate negotiation. Each LLM is guided by a matched Five-Factor personality profile to control for individual variation and enhance realism. We evaluate alignment across three dimensions: linguistic style, emotional expression (e.g., anger dynamics), and strategic behavior. GPT-4.1 achieves the closest alignment with humans in linguistic style and emotional dynamics, while Claude-3.7-Sonnet best reflects strategic behavior. Nonetheless, substantial alignment gaps persist. Our findings establish a benchmark for alignment between LLMs and humans in socially complex interactions, underscoring both the promise and the limitations of personality conditioning in dialogue modeling.

Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns over data confidentiality remain a significant barrier to model-sharing adoption, as Confidential Property Inference (CPI) attacks can exploit shared ML models to uncover confidential properties of the model provider's private model training data. Existing defenses often assume that CPI attacks are non-adaptive to the specific ML model they are targeting. This assumption overlooks a key characteristic of real-world adversaries: their responsiveness, i.e., adversaries' ability to dynamically adjust their attack models based on the information of the target and its defenses. To overcome this limitation, we propose a novel defense method that explicitly accounts for the responsive nature of real-world adversaries via two methodological innovations: a novel Responsive CPI attack and an attack-defense arms race framework. The former emulates the responsive behaviors of adversaries in the real world, and the latter iteratively enhances both the target and attack models, ultimately producing a secure ML model that is robust against responsive CPI attacks. Furthermore, we propose and integrate a novel approximate strategy into our defense, which addresses a critical computational bottleneck of defense methods and improves defense efficiency. Through extensive empirical evaluations across various realistic model-sharing scenarios, we demonstrate that our method outperforms existing defenses by more effectively defending against CPI attacks, preserving ML model utility, and reducing computational overhead.

As the field of artificial intelligence (AI) and machine learning (ML) continues to prioritize fairness and the concern for historically marginalized communities, the importance of intersectionality in AI research has gained significant recognition. However, few studies provide practical guidance on how researchers can effectively incorporate intersectionality into critical praxis. In response, this paper presents a comprehensive framework grounded in critical reflexivity as intersectional praxis. Operationalizing intersectionality within the AI/DS (Artificial Intelligence/Data Science) pipeline, Quantitative Intersectional Data (QUINTA) is introduced as a methodological paradigm that challenges conventional and superficial research habits, particularly in data-centric processes, to identify and mitigate negative impacts such as the inadvertent marginalization caused by these practices. The framework centers researcher reflexivity to call attention to the AI researchers' power in creating and analyzing AI/DS artifacts through data-centric approaches. To illustrate the effectiveness of QUINTA, we provide a reflexive AI/DS researcher demonstration utilizing the \#metoo movement as a case study. Note: This paper was accepted as a poster presentation at Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) Conference in 2023.

Large Language Model (LLM)-based agents have emerged as a new paradigm that extends LLMs' capabilities beyond text generation to dynamic interaction with external environments. By integrating reasoning with perception, memory, and tool use, agents are increasingly deployed in diverse domains like web navigation and household robotics. A critical challenge, however, lies in ensuring agent generalizability - the ability to maintain consistent performance across varied instructions, tasks, environments, and domains, especially those beyond agents' fine-tuning data. Despite growing interest, the concept of generalizability in LLM-based agents remains underdefined, and systematic approaches to measure and improve it are lacking. In this survey, we provide the first comprehensive review of generalizability in LLM-based agents. We begin by emphasizing agent generalizability's importance by appealing to stakeholders and clarifying the boundaries of agent generalizability by situating it within a hierarchical domain-task ontology. We then review datasets, evaluation dimensions, and metrics, highlighting their limitations. Next, we categorize methods for improving generalizability into three groups: methods for the backbone LLM, for agent components, and for their interactions. Moreover, we introduce the distinction between generalizable frameworks and generalizable agents and outline how generalizable frameworks can be translated into agent-level generalizability. Finally, we identify critical challenges and future directions, including developing standardized frameworks, variance- and cost-based metrics, and approaches that integrate methodological innovations with architecture-level designs. By synthesizing progress and highlighting opportunities, this survey aims to establish a foundation for principled research on building LLM-based agents that generalize reliably across diverse applications.

Function calling (FC) has emerged as a powerful technique for facilitating large language models (LLMs) to interact with external systems and perform structured tasks. However, the mechanisms through which it influences model behavior remain largely under-explored. Besides, we discover that in addition to the regular usage of FC, this technique can substantially enhance the compliance of LLMs with user instructions. These observations motivate us to leverage causality, a canonical analysis method, to investigate how FC works within LLMs. In particular, we conduct layer-level and token-level causal interventions to dissect FC's impact on the model's internal computational logic when responding to user queries. Our analysis confirms the substantial influence of FC and reveals several in-depth insights into its mechanisms. To further validate our findings, we conduct extensive experiments comparing the effectiveness of FC-based instructions against conventional prompting methods. We focus on enhancing LLM safety robustness, a critical LLM application scenario, and evaluate four mainstream LLMs across two benchmark datasets. The results are striking: FC shows an average performance improvement of around 135% over conventional prompting methods in detecting malicious inputs, demonstrating its promising potential to enhance LLM reliability and capability in practical applications.

Two central capabilities of language models (LMs) are: (i) drawing on prior knowledge about entities, which allows them to answer queries such as "What's the official language of Austria?", and (ii) adapting to new information provided in context, e.g., "Pretend the official language of Austria is Tagalog.", that is pre-pended to the question. In this article, we introduce targeted persuasion score (TPS), designed to quantify how persuasive a given context is to an LM where persuasion is operationalized as the ability of the context to alter the LM's answer to the question. In contrast to evaluating persuasiveness only by inspecting the greedily decoded answer under the model, TPS provides a more fine-grained view of model behavior. Based on the Wasserstein distance, TPS measures how much a context shifts a model's original answer distribution toward a target distribution. Empirically, through a series of experiments, we show that TPS captures a more nuanced notion of persuasiveness than previously proposed metrics.