Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence mechanisms, such as model fine-tuning or output censorship using LLMs, have proven to be fallible, as LLMs can still generate problematic responses. Commonly employed censorship approaches treat the issue as a machine learning problem and rely on another LM to detect undesirable content in LLM outputs. In this paper, we present the theoretical limitations of such semantic censorship approaches. Specifically, we demonstrate that semantic censorship can be perceived as an undecidable problem, highlighting the inherent challenges in censorship that arise due to LLMs' programmatic and instruction-following capabilities. Furthermore, we argue that the challenges extend beyond semantic censorship, as knowledgeable attackers can reconstruct impermissible outputs from a collection of permissible ones. As a result, we propose that the problem of censorship needs to be reevaluated; it should be treated as a security problem which warrants the adaptation of security-based approaches to mitigate potential risks.

Yet, these considerations are often overlooked, leading to issues of bias, discrimination, and perceived untrustworthiness. In response, we conducted a Systematic Review to unearth challenges and solutions relating to D&I in AI. Our rigorous search yielded 48 research articles published between 2017 and 2022. Open coding of these papers revealed 55 unique challenges and 33 solutions for D&I in AI, as well as 24 unique challenges and 23 solutions for enhancing such practices using AI. This study, by offering a deeper understanding of these issues, will enlighten researchers and practitioners seeking to integrate these principles into future AI systems.

Artificial intelligence researchers have made significant advances in legal intelligence in recent years. However, the existing studies have not focused on the important value embedded in judgments reversals, which limits the improvement of the efficiency of legal intelligence. In this paper, we propose a causal Framework for Accurately Inferring case Reversals (FAIR), which models the problem of judgments reversals based on real Chinese judgments. We mine the causes of judgments reversals by causal inference methods and inject the obtained causal relationships into the neural network as a priori knowledge. And then, our framework is validated on a challenging dataset as a legal judgment prediction task. The experimental results show that our framework can tap the most critical factors in judgments reversal, and the obtained causal relationships can effectively improve the neural network's performance. In addition, we discuss the generalization ability of large language models for legal intelligence tasks using ChatGPT as an example. Our experiment has found that the generalization ability of large language models still has defects, and mining causal relationships can effectively improve the accuracy and explain ability of model predictions.

These notions vary across conceptualization Intersectionality is a critical framework that, through inquiry and (e.g., group, individual fairness [8]) and operationalization (e.g., praxis, allows us to examine how social inequalities persist through pre/in/post-processing [2]) [54]; nevertheless, the literature generally domains of structure and discipline. Given AI fairness' raison d'être agrees on the goal of minimizing negative outcomes across of "fairness," we argue that adopting intersectionality as an analytical demographic groups, including groups associated with multiple, framework is pivotal to effectively operationalizing fairness. "intersectional" demographic attributes (e.g., Black women) [92]. Through a critical review of how intersectionality is discussed in However, Kong [66] observes that AI fairness papers often narrowly 30 papers from the AI fairness literature, we deductively and inductively: interpret intersectional subgroup fairness as intersectionality, the 1) map how intersectionality tenets operate within the critical framework from which the term originates [29, 67]. This AI fairness paradigm and 2) uncover gaps between the conceptualization myopic conceptualization of intersectionality has non-trivial consequences and operationalization of intersectionality. We find that for just AI design and epistemology (i.e., ways of knowing).

It is every parent's worst nightmare - an image or video of your child you posted to social media ends up on a sexually explicit website. Some had their children preyed on by pedophiles - who are becoming increasingly sophisticated with tech like AI - turned into cruel memes by trolls or had their identities stolen by hackers. These scenarios have been highlighted in a new advert aimed at warning parents about the dangers of oversharing on social media. Recent studies show the average child has their picture shared online 1,300 times before the age of 13, and the advertisement suggests that it takes just one photo and AI to recreate innocent children in ways most parents could never imagine. The ad revealed it takes just one photo and AI to ruin a child's future.

WASHINGTON--The Federal Trade Commission's investigation into the ChatGPT app points to an emerging conflict over how Washington should regulate artificial intelligence, one that could pit some of America's biggest businesses against labor unions and progressive advocacy groups.

Margaret Atwood, Jonathan Franzen, James Patterson, Suzanne Collins and Viet Thanh Nguyen are among the prominent authors endorsing the letter addressed to the CEOs of OpenAI, Meta, Microsoft, Alphabet, IBM and Stability AI. In the letter organised by the Authors Guild, the largest professional writers' organisation in the United States, the signatories call attention to the "inherent injustice in exploiting our works as part of your AI systems without our consent, credit, or compensation". "These technologies mimic and regurgitate our language, stories, style, and ideas. "You're spending billions of dollars to develop AI technology. It is only fair that you compensate us for using our writings, without which AI would be banal and extremely limited."

In this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes two drawbacks of existing approaches. First, our model does not assume that participants agree on the structure of the debate. It does this by allowing participants to express their opinion about all aspects of the debate. Second, our model does not assume that participants' opinions are rational, an assumption that significantly limits current approaches. Instead, we define a weaker notion of rationality that characterises coherent opinions, and we consider different scenarios based on the coherence of individual opinions and the level of consensus. We provide a formal analysis of different opinion aggregation functions that compute a collective decision based on the individual opinions and the debate structure. In particular, we demonstrate that aggregated opinions can be coherent even if there is a lack of consensus and individual opinions are not coherent. We conclude with an empirical evaluation demonstrating that collective opinions can be computed efficiently for real-sized debates.

Generative language models produce highly abstractive outputs by design, in contrast to extractive responses in search engines. Given this characteristic of LLMs and the resulting implications for content Licensing & Attribution, we propose the the so-called Extractive-Abstractive axis for benchmarking generative models and highlight the need for developing corresponding metrics, datasets and annotation guidelines. We limit our discussion to the text modality.

Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its domain-customized data which can potentially also include their users' PII. In order to comply with privacy laws such as the "right to be forgotten", the data points of users that are most vulnerable to extraction could be deleted. We find that once the most vulnerable points are deleted, a new set of points become vulnerable to extraction. So far, little attention has been given to understanding memorization for fine-tuned models. In this work, we also show that not only do fine-tuned models leak their training data but they also leak the pre-training data (and PII) memorized during the pre-training phase. The property of new data points becoming vulnerable to extraction after unlearning and leakage of pre-training data through fine-tuned models can pose significant privacy and legal concerns for companies that use LLMs to offer services. We hope this work will start an interdisciplinary discussion within AI and law communities regarding the need for policies to tackle these issues.