For instance, (Rastegarpanah Existing work in fairness audits assumes that et al., 2021) proposes to study the illegal use of some profile agents operate independently. In this paper, we data in the response of a model in such a query-response consider the case of multiple agents auditing the setup. Yet, as of today, an auditor performs her audit tasks same platform for different tasks. Agents have on each attribute of interest sequentially, one after the other, two levers: their collaboration strategy, with or and independent of other auditors. For example, when she without coordination beforehand, and their sampling wants to audit an ML model that predicts whether it is safe method. We theoretically study their interplay to issue a loan (Feldman et al., 2015), she begins by auditing when agents operate independently or collaborate.

Fervent calls for more robust governance of the harms associated with artificial intelligence (AI) are leading to the adoption around the world of what regulatory scholars have called a management-based approach to regulation. Recent initiatives in the United States and Europe, as well as the adoption of major self-regulatory standards by the International Organization for Standardization, share in common a core management-based paradigm. These management-based initiatives seek to motivate an increase in human oversight of how AI tools are trained and developed. Refinements and systematization of human-guided training techniques will thus be needed to fit within this emerging era of management-based regulatory paradigm. If taken seriously, human-guided training can alleviate some of the technical and ethical pressures on AI, boosting AI performance with human intuition as well as better addressing the needs for fairness and effective explainability. In this paper, we discuss the connection between the emerging management-based regulatory frameworks governing AI and the need for human oversight during training. We broadly cover some of the technical components involved in human-guided training and then argue that the kinds of high-stakes use cases for AI that appear of most concern to regulators should lean more on human-guided training than on data-only training. We hope to foster a discussion between legal scholars and computer scientists involving how to govern a domain of technology that is vast, heterogenous, and dynamic in its applications and risks.

XAI (eXplanable AI) techniques that have the property of explaining the reasons for their conclusions, i.e. explainability or interpretability, are attracting attention. XAI is expected to be used in the development of forensic science and the justice system. In today's forensic and criminal investigation environment, experts face many challenges due to large amounts of data, small pieces of evidence in a chaotic and complex environment, traditional laboratory structures and sometimes inadequate knowledge. All these can lead to failed investigations and miscarriages of justice. In this paper, we describe the application of one logical approach to crime scene investigation. The subject of the application is ``The Adventure of the Speckled Band'' from the Sherlock Holmes short stories. The applied data is the knowledge graph created for the Knowledge Graph Reasoning Challenge. We tried to find the murderer by inferring each person with the motive, opportunity, and method. We created an ontology of motives and methods of murder from dictionaries and dictionaries, added it to the knowledge graph of ``The Adventure of the Speckled Band'', and applied scripts to determine motives, opportunities, and methods.

Machine Learning (ML) and 'Artificial Intelligence' ('AI') methods tend to replicate and amplify existing biases and prejudices, as do Robots with AI. For example, robots with facial recognition have failed to identify Black Women as human, while others have categorized people, such as Black Men, as criminals based on appearance alone. A 'culture of modularity' means harms are perceived as 'out of scope', or someone else's responsibility, throughout employment positions in the 'AI supply chain'. Incidents are routine enough (incidentdatabase.ai lists over 2000 examples) to indicate that few organizations are capable of completely respecting peoples' rights; meeting claimed equity, diversity, and inclusion (EDI or DEI) goals; or recognizing and then addressing such failures in their organizations and artifacts. We propose a framework for adapting widely practiced Research and Development (R&D) project management methodologies to build organizational equity capabilities and better integrate known evidence-based best practices. We describe how project teams can organize and operationalize the most promising practices, skill sets, organizational cultures, and methods to detect and address rights-based fairness, equity, accountability, and ethical problems as early as possible when they are often less harmful and easier to mitigate; then monitor for unforeseen incidents to adaptively and constructively address them. Our primary example adapts an Agile development process based on Scrum, one of the most widely adopted approaches to organizing R&D teams. We also discuss limitations of our proposed framework and future research directions.

In 1976, Frank Collin, an ambitious leader in the small but resilient Nazi party of the United States, planned a march in Skokie, Illinois--an attempt to raise the profile of his organization and build support for his cause. The town, many of whose residents were Jewish and had lived through the war, vehemently opposed the demonstration, and the case went to the courts. The American Civil Liberties Union came to the legal defense of Collin and his fellow Nazis on First Amendment grounds--a move that would be almost unthinkable today. Aryeh Neier, the national executive director of the ACLU at the time, received thousands of letters condemning his organization's decision to defend the free speech rights of Nazis. Neier was born into a Jewish family in Berlin in 1937 and fled from Germany to England along with his parents as a child.

We apply causal mediation analysis to explain the decision-making process of neural models for rumour detection on Twitter. Interventions at the input and network level reveal the causal impacts of tweets and words in the model output. We find that our approach CMA-R -- Causal Mediation Analysis for Rumour detection -- identifies salient tweets that explain model predictions and show strong agreement with human judgements for critical tweets determining the truthfulness of stories. CMA-R can further highlight causally impactful words in the salient tweets, providing another layer of interpretability and transparency into these blackbox rumour detection systems. Code is available at: https://github.com/ltian678/cma-r.

Recently text-to-image models have gained widespread attention in the community due to their controllable and high-quality generation ability. However, the robustness of such models and their potential ethical issues have not been fully explored. In this paper, we introduce Universal Semantic Trigger, a meaningless token sequence that can be added at any location within the input text yet can induce generated images towards a preset semantic target.To thoroughly investigate it, we propose Semantic Gradient-based Search (SGS) framework. SGS automatically discovers the potential universal semantic triggers based on the given semantic targets. Furthermore, we design evaluation metrics to comprehensively evaluate semantic shift of images caused by these triggers. And our empirical analyses reveal that the mainstream open-source text-to-image models are vulnerable to our triggers, which could pose significant ethical threats. Our work contributes to a further understanding of text-to-image synthesis and helps users to automatically auditing their models before deployment.

How can individuals exchange information to learn from each other despite their privacy needs and security concerns? For example, consider individuals deliberating a contentious topic and being concerned about divulging their private experiences. Preserving individual privacy and enabling efficient social learning are both important desiderata but seem fundamentally at odds with each other and very hard to reconcile. We do so by controlling information leakage using rigorous statistical guarantees that are based on differential privacy (DP). Our agents use log-linear rules to update their beliefs after communicating with their neighbors. Adding DP randomization noise to beliefs provides communicating agents with plausible deniability with regard to their private information and their network neighborhoods. We consider two learning environments one for distributed maximum-likelihood estimation given a finite number of private signals and another for online learning from an infinite, intermittent signal stream. Noisy information aggregation in the finite case leads to interesting tradeoffs between rejecting low-quality states and making sure all high-quality states are accepted in the algorithm output. Our results flesh out the nature of the trade-offs in both cases between the quality of the group decision outcomes, learning accuracy, communication cost, and the level of privacy protections that the agents are afforded.

This study explores the potential of LLMs to augment judgement in forecasting tasks. We evaluated the impact on forecasting accuracy of two GPT-4-Turbo assistants: one designed to provide high-quality advice ('superforecasting'), and the other designed to be overconfident and base-rate-neglecting. Participants (N = 991) had the option to consult their assigned LLM assistant throughout the study, in contrast to a control group that used a less advanced model (DaVinci-003) without direct forecasting support. Our preregistered analyses reveal that LLM augmentation significantly enhances forecasting accuracy by 23% across both types of assistants, compared to the control group. This improvement occurs despite the superforecasting assistant's higher accuracy in predictions, indicating the augmentation's benefit is not solely due to model prediction accuracy. Exploratory analyses showed a pronounced effect in one forecasting item, without which we find that the superforecasting assistant increased accuracy by 43%, compared with 28% for the biased assistant. We further examine whether LLM augmentation disproportionately benefits less skilled forecasters, degrades the wisdom-of-the-crowd by reducing prediction diversity, or varies in effectiveness with question difficulty. Our findings do not consistently support these hypotheses. Our results suggest that access to an LLM assistant, even a biased one, can be a helpful decision aid in cognitively demanding tasks where the answer is not known at the time of interaction.

Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. Despite extensive research on traditional machine learning models, there has been limited work studying MIA on the pre-training data of large language models (LLMs). We perform a large-scale evaluation of MIAs over a suite of language models (LMs) trained on the Pile, ranging from 160M to 12B parameters. We find that MIAs barely outperform random guessing for most settings across varying LLM sizes and domains. Our further analyses reveal that this poor performance can be attributed to (1) the combination of a large dataset and few training iterations, and (2) an inherently fuzzy boundary between members and non-members. We identify specific settings where LLMs have been shown to be vulnerable to membership inference and show that the apparent success in such settings can be attributed to a distribution shift, such as when members and non-members are drawn from the seemingly identical domain but with different temporal ranges. We release our code and data as a unified benchmark package that includes all existing MIAs, supporting future work.