Three people have been jailed in the kidnapping and killing of a Hmong American comedian and activist who was found dead near Medellín after going out to meet a woman he reportedly met on social media, Colombian officials announced Thursday. The Prosecutor's Office said in a statement that two men and a woman were charged with the crimes of aggravated kidnapping for extortion and aggravated homicide in the death last month of Tou Ger Xiong, 50. The suspects denied the charges at a hearing, the statement said. A minor who presented himself to the Public Prosecutor's Office admitting to having participated in the crime also was charged in the case and transferred to a special detention center for minors, it added. The U.S. Embassy in Bogota warned a week ago about Colombian criminals who use dating apps to lure victims and then assault and rob them.

Kismet Jackson used to carry her handgun just about everywhere in San Bernardino County. To get her nails done. To pick up her prescription. To hang out with her grandchildren. For her, it was all about staying safe. "Being out and about, you just want to protect yourself," explained Jackson, an Air Force veteran and member of the National African American Gun Assn.

The older Sefala became, the more she peppered her father with questions about the visible racial segregation of their neighborhood: "Why is it like this?" Now, at 28, she is helping do something about it. Alongside computer scientists Nyalleng Moorosi and Timnit Gebru at the nonprofit Distributed AI Research Institute (DAIR), which Gebru set up in 2021, she is deploying computer vision tools and satellite images to analyze the impacts of racial segregation in housing, with the ultimate hope that their work will help to reverse it. "We still see previously marginalized communities' lives not improving," says Sefala. Though she was never alive during the apartheid regime, she has still been affected by its awful enduring legacy: "It's just very unequal, very frustrating." In South Africa, the government census categorizes both wealthier suburbs and townships, a creation of apartheid and typically populated by Black people, as "formal residential neighborhoods."

Large language models (LLMs), while promising, face criticisms for biases, hallucinations, and a lack of reasoning capability. This paper introduces SocraSynth, a multi-LLM agent reasoning platform developed to mitigate these issues. SocraSynth utilizes conditional statistics and systematic context enhancement through continuous arguments, alongside adjustable debate contentiousness levels. The platform typically involves a human moderator and two LLM agents representing opposing viewpoints on a given subject. SocraSynth operates in two main phases: knowledge generation and reasoning evaluation. In the knowledge generation phase, the moderator defines the debate topic and contentiousness level, prompting the agents to formulate supporting arguments for their respective stances. The reasoning evaluation phase then employs Socratic reasoning and formal logic principles to appraise the quality of the arguments presented. The dialogue concludes with the moderator adjusting the contentiousness from confrontational to collaborative, gathering final, conciliatory remarks to aid in human reasoning and decision-making. Through case studies in three distinct application domains, this paper showcases SocraSynth's effectiveness in fostering rigorous research, dynamic reasoning, comprehensive assessment, and enhanced collaboration. This underscores the value of multi-agent interactions in leveraging LLMs for advanced knowledge extraction and decision-making support.

Case law plays a crucial role in legal research, particularly in the context of human rights. Many international human rights conventions, such as the European Convention on Human Rights (ECHR), are considered'living instruments', which means that human rights should be interpreted in light of present-day conditions and in accordance with developments in international law [1]. Fundamental human rights, such as the right to respect for private and family life, home, and correspondence as enshrined in Article 8 of the ECHR, serve as broad normative standards that (may) evolve in response to societal changes and international consensus. For example, the meaning of'correspondence' has significantly changed with the internet and the progression of technology, and also what is considered'family life' [2] or a'home' is ever-developing [3]. Consequently, the interpretation and application of human rights undergo continuous development, requiring legal scholars and practitioners to rely heavily on the case law established by international courts, such as the European Court of Human Rights (ECtHR). However, the volume of case law is ever-increasing, which makes it challenging for legal scholars to discover relevant cases and gain a comprehensive understanding of this vast amount of information.

We study federated unlearning, a novel problem to eliminate the impact of specific clients or data points on the global model learned via federated learning (FL). This problem is driven by the right to be forgotten and the privacy challenges in FL. We introduce a new framework for exact federated unlearning that meets two essential criteria: \textit{communication efficiency} and \textit{exact unlearning provability}. To our knowledge, this is the first work to tackle both aspects coherently. We start by giving a rigorous definition of \textit{exact} federated unlearning, which guarantees that the unlearned model is statistically indistinguishable from the one trained without the deleted data. We then pinpoint the key property that enables fast exact federated unlearning: total variation (TV) stability, which measures the sensitivity of the model parameters to slight changes in the dataset. Leveraging this insight, we develop a TV-stable FL algorithm called \texttt{FATS}, which modifies the classical \texttt{\underline{F}ed\underline{A}vg} algorithm for \underline{T}V \underline{S}tability and employs local SGD with periodic averaging to lower the communication round. We also design efficient unlearning algorithms for \texttt{FATS} under two settings: client-level and sample-level unlearning. We provide theoretical guarantees for our learning and unlearning algorithms, proving that they achieve exact federated unlearning with reasonable convergence rates for both the original and unlearned models. We empirically validate our framework on 6 benchmark datasets, and show its superiority over state-of-the-art methods in terms of accuracy, communication cost, computation cost, and unlearning efficacy.

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and enhancing the safety and robustness of these models. This paper investigates the intricate consequences of such modifications through model editing, uncovering a complex relationship between enhancing model accuracy and preserving its ethical integrity. Our in-depth analysis reveals a striking paradox: while injecting accurate information is crucial for model reliability, it can paradoxically destabilize the model's foundational framework, resulting in unpredictable and potentially unsafe behaviors. Additionally, we propose a benchmark dataset NicheHazardQA to investigate this unsafe behavior both within the same and cross topical domain. This aspect of our research sheds light on how the edits, impact the model's safety metrics and guardrails. Our findings show that model editing serves as a cost-effective tool for topical red-teaming by methodically applying targeted edits and evaluating the resultant model behavior

While colonization has sociohistorically impacted people's identities across various dimensions, those colonial values and biases continue to be perpetuated by sociotechnical systems. One category of sociotechnical systems--sentiment analysis tools--can also perpetuate colonial values and bias, yet less attention has been paid to how such tools may be complicit in perpetuating coloniality, although they are often used to guide various practices (e.g., content moderation). In this paper, we explore potential bias in sentiment analysis tools in the context of Bengali communities that have experienced and continue to experience the impacts of colonialism. Drawing on identity categories most impacted by colonialism amongst local Bengali communities, we focused our analytic attention on gender, religion, and nationality. We conducted an algorithmic audit of all sentiment analysis tools for Bengali, available on the Python package index (PyPI) and GitHub. Despite similar semantic content and structure, our analyses showed that in addition to inconsistencies in output from different tools, Bengali sentiment analysis tools exhibit bias between different identity categories and respond differently to different ways of identity expression. Connecting our findings with colonially shaped sociocultural structures of Bengali communities, we discuss the implications of downstream bias of sentiment analysis tools.

This paper introduces INACIA (Instru\c{c}\~ao Assistida com Intelig\^encia Artificial), a groundbreaking system designed to integrate Large Language Models (LLMs) into the operational framework of Brazilian Federal Court of Accounts (TCU). The system automates various stages of case analysis, including basic information extraction, admissibility examination, Periculum in mora and Fumus boni iuris analyses, and recommendations generation. Through a series of experiments, we demonstrate INACIA's potential in extracting relevant information from case documents, evaluating its legal plausibility, and formulating propositions for judicial decision-making. Utilizing a validation dataset alongside LLMs, our evaluation methodology presents an innovative approach to assessing system performance, correlating highly with human judgment. The results highlight INACIA's proficiency in handling complex legal tasks, indicating its suitability for augmenting efficiency and judicial fairness within legal systems. The paper also discusses potential enhancements and future applications, positioning INACIA as a model for worldwide AI integration in legal domains.

In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled from a large volume of annotated examples, finding the right prompt may result in high annotation costs. To address this challenge, this paper introduces an influence-driven selective annotation method that aims to minimize annotation costs while improving the quality of in-context examples. The essence of our method is to select a pivotal subset from a large-scale unlabeled data pool to annotate for the subsequent sampling of prompts. Specifically, a directed graph is first constructed to represent unlabeled data. Afterward, the influence of candidate unlabeled subsets is quantified with a diffusion process. A simple yet effective greedy algorithm for unlabeled data selection is lastly introduced. It iteratively selects the data if it provides a maximum marginal gain with respect to quantified influence. Compared with previous efforts on selective annotations, our influencedriven method works in an end-to-end manner, avoids an intractable explicit balance between data diversity and representativeness, and enjoys theoretical support. Experiments confirm the superiority of the proposed method on various benchmarks, achieving better performance under lower time consumption during subset selection. The project page is available at https://skzhang1.github.io/IDEAL/. In-context learning (ICL) entails presenting a small set of examples with demonstrations as prompts (called in-context examples) to large language models (LLMs), before making predictions on test inputs (Wei et al., 2022a; Min et al., 2022; Akyürek et al., 2023). This emerging few-shot learning paradigm is an appealing alternative to supervised fine-tuning as it can avoid heavy parameter updates of language models while improving accuracy (Liu et al., 2021; Yoo et al., 2022). Recent studies indicate that obtaining prompts from a vast collection of annotated examples is crucial to achieving strong performance (Rubin et al., 2022). Notably, these studies have illuminated the substantial performance improvements when retrieving analogous examples (under specific embedding criteria) as in-context examples tailored for each individual test input.