Employing Large Language Models (LLM) in various downstream applications such as classification is crucial, especially for smaller companies lacking the expertise and resources required for fine-tuning a model. Fairness in LLMs helps ensure inclusivity, equal representation based on factors such as race, gender and promotes responsible AI deployment. As the use of LLMs has become increasingly prevalent, it is essential to assess whether LLMs can generate fair outcomes when subjected to considerations of fairness. In this study, we introduce a framework outlining fairness regulations aligned with various fairness definitions, with each definition being modulated by varying degrees of abstraction. We explore the configuration for in-context learning and the procedure for selecting in-context demonstrations using RAG, while incorporating fairness rules into the process. Experiments conducted with different LLMs indicate that GPT-4 delivers superior results in terms of both accuracy and fairness compared to other models. This work is one of the early attempts to achieve fairness in prediction tasks by utilizing LLMs through in-context learning.

OpenAI said in a filing in Manhattan federal court on Monday that the Times caused the technology to reproduce its material through "deceptive prompts that blatantly violate OpenAI's terms of use". "The allegations in the Times's complaint do not meet its famously rigorous journalistic standards," OpenAI said. "The truth, which will come out in the course of this case, is that the Times paid someone to hack OpenAI's products." OpenAI did not name the "hired gun" whom it said the Times used to manipulate its systems and did not accuse the newspaper of breaking any anti-hacking laws. Representatives for the New York Times and OpenAI did not immediately respond to requests for comment on the filing. The Times sued OpenAI and its largest financial backer, Microsoft, in December, accusing them of using millions of its articles without permission to train chatbots to provide information to users.

The extensive industrialization of artificial intelligence (AI) since the mid-2010s has increasingly motivated artists to address its economic and sociopolitical consequences. In this chapter, I discuss interrelated art practices that thematize creative agency, crowdsourced labor, and delegated artmaking to reveal the social rootage of AI technologies and underline the productive human roles in their development. I focus on works whose poetic features indicate broader issues of contemporary AI-influenced science, technology, economy, and society. By exploring the conceptual, methodological, and ethical aspects of their effectiveness in disrupting the political regime of corporate AI, I identify several problems that affect their tactical impact and outline potential avenues for tackling the challenges and advancing the field.

In this paper we hope to identify how the typical or standard artificial intelligence development process encourages or facilitates the creation of racialized technologies. We begin by understanding Sylvia Wynter's definition of the biocentric Man genre and its exclusion of Blackness from humanness. We follow this with outlining what we consider to be the typical steps for developing an AI-based technology, which we have broken down into 6 stages: identifying a problem, development process and management tool selection, dataset development and data processing, model development, deployment and risk assessment, and integration and monitoring. The goal of this paper is to better understand how Wynter's biocentric Man is being represented and reinforced by the technologies we are producing in the AI lifecycle and by the lifecycle itself; we hope to identify ways in which the distinction of Blackness from the "ideal" human leads to perpetual punishment at the hands of these technologies. By deconstructing this development process, we can potentially identify ways in which humans in general have not been prioritized and how those affects are disproportionately affecting marginalized people. We hope to offer solutions that will encourage changes in the AI development cycle.

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, we focus on open foundation models, defined here as those with broadly available model weights (e.g. Llama 2, Stable Diffusion XL). We identify five distinctive properties (e.g. greater customizability, poor monitoring) of open foundation models that lead to both their benefits and risks. Open foundation models present significant benefits, with some caveats, that span innovation, competition, the distribution of decision-making power, and transparency. To understand their risks of misuse, we design a risk assessment framework for analyzing their marginal risk. Across several misuse vectors (e.g. cyberattacks, bioweapons), we find that current research is insufficient to effectively characterize the marginal risk of open foundation models relative to pre-existing technologies. The framework helps explain why the marginal risk is low in some cases, clarifies disagreements about misuse risks by revealing that past work has focused on different subsets of the framework with different assumptions, and articulates a way forward for more constructive debate. Overall, our work helps support a more grounded assessment of the societal impact of open foundation models by outlining what research is needed to empirically validate their theoretical benefits and risks.

The rapid advancement of generative AI is poised to disrupt the creative industry. Amidst the immense excitement for this new technology, its future development and applications in the creative industry hinge crucially upon two copyright issues: 1) the compensation to creators whose content has been used to train generative AI models (the fair use standard); and 2) the eligibility of AI-generated content for copyright protection (AI-copyrightability). While both issues have ignited heated debates among academics and practitioners, most analysis has focused on their challenges posed to existing copyright doctrines. In this paper, we aim to better understand the economic implications of these two regulatory issues and their interactions. By constructing a dynamic model with endogenous content creation and AI model development, we unravel the impacts of the fair use standard and AI-copyrightability on AI development, AI company profit, creators income, and consumer welfare, and how these impacts are influenced by various economic and operational factors. For example, while generous fair use (use data for AI training without compensating the creator) benefits all parties when abundant training data exists, it can hurt creators and consumers when such data is scarce. Similarly, stronger AI-copyrightability (AI content enjoys more copyright protection) could hinder AI development and reduce social welfare. Our analysis also highlights the complex interplay between these two copyright issues. For instance, when existing training data is scarce, generous fair use may be preferred only when AI-copyrightability is weak. Our findings underscore the need for policymakers to embrace a dynamic, context-specific approach in making regulatory decisions and provide insights for business leaders navigating the complexities of the global regulatory environment.

Large Language Models (LLMs) become the start-of-the-art solutions for a variety of natural language tasks and are integrated into real-world applications. However, LLMs can be potentially harmful in manifesting undesirable safety issues like social biases and toxic content. It is imperative to assess its safety issues before deployment. However, the quality and diversity of test prompts generated by existing methods are still far from satisfactory. Not only are these methods labor-intensive and require large budget costs, but the controllability of test prompt generation is lacking for the specific testing domain of LLM applications. With the idea of LLM for LLM testing, we propose the first LLM, called TroubleLLM, to generate controllable test prompts on LLM safety issues. Extensive experiments and human evaluation illustrate the superiority of TroubleLLM on generation quality and generation controllability.

We study existing approaches to leverage off-the-shelf Natural Language Inference (NLI) models for the evaluation of summary faithfulness and argue that these are sub-optimal due to the granularity level considered for premises and hypotheses. That is, the smaller content unit considered as hypothesis is a sentence and premises are made up of a fixed number of document sentences. We propose a novel approach, namely InFusE, that uses a variable premise size and simplifies summary sentences into shorter hypotheses. Departing from previous studies which focus on single short document summarisation, we analyse NLI based faithfulness evaluation for diverse summarisation tasks. We introduce DiverSumm, a new benchmark comprising long form summarisation (long documents and summaries) and diverse summarisation tasks (e.g., meeting and multi-document summarisation). In experiments, InFusE obtains superior performance across the different summarisation tasks. Our code and data are available at https://github.com/HJZnlp/infuse.

Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 and HotpotQA mainly study ``known unknowns'' with clear indications of both what information is missing, and how to find it to answer the question. Hence, good performance on these benchmarks provides a false sense of security. A yet unmet need of the NLP community is a bank of non-factoid, multi-perspective questions involving a great deal of unclear information needs, i.e. ``unknown uknowns''. We claim we can find such questions in search engine logs, which is surprising because most question-intent queries are indeed factoid. We present Researchy Questions, a dataset of search engine queries tediously filtered to be non-factoid, ``decompositional'' and multi-perspective. We show that users spend a lot of ``effort'' on these questions in terms of signals like clicks and session length, and that they are also challenging for GPT-4. We also show that ``slow thinking'' answering techniques, like decomposition into sub-questions shows benefit over answering directly. We release $\sim$ 100k Researchy Questions, along with the Clueweb22 URLs that were clicked.

This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that sustains and nurtures the development of LLMs. Consequently, examination of these datasets emerges as a critical topic in research. In order to address the current lack of a comprehensive overview and thorough analysis of LLM datasets, and to gain insights into their current status and future trends, this survey consolidates and categorizes the fundamental aspects of LLM datasets from five perspectives: (1) Pre-training Corpora; (2) Instruction Fine-tuning Datasets; (3) Preference Datasets; (4) Evaluation Datasets; (5) Traditional Natural Language Processing (NLP) Datasets. The survey sheds light on the prevailing challenges and points out potential avenues for future investigation. Additionally, a comprehensive review of the existing available dataset resources is also provided, including statistics from 444 datasets, covering 8 language categories and spanning 32 domains. Information from 20 dimensions is incorporated into the dataset statistics. The total data size surveyed surpasses 774.5 TB for pre-training corpora and 700M instances for other datasets. We aim to present the entire landscape of LLM text datasets, serving as a comprehensive reference for researchers in this field and contributing to future studies. Related resources are available at: https://github.com/lmmlzn/Awesome-LLMs-Datasets.