Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on large unsanitised corpora of source code scraped from the internet. The content of these datasets is memorised and can be extracted by attackers with data extraction attacks. In this work, we explore memorisation in large language models for code and compare the rate of memorisation with large language models trained on natural language. We adopt an existing benchmark for natural language and construct a benchmark for code by identifying samples that are vulnerable to attack. We run both benchmarks against a variety of models, and perform a data extraction attack. We find that large language models for code are vulnerable to data extraction attacks, like their natural language counterparts. From the training data that was identified to be potentially extractable we were able to extract 47% from a CodeGen-Mono-16B code completion model. We also observe that models memorise more, as their parameter count grows, and that their pre-training data are also vulnerable to attack. We also find that data carriers are memorised at a higher rate than regular code or documentation and that different model architectures memorise different samples. Data leakage has severe outcomes, so we urge the research community to further investigate the extent of this phenomenon using a wider range of models and extraction techniques in order to build safeguards to mitigate this issue.

This article studies how to intervene against statistical discrimination, when it is based on beliefs generated by machine learning, rather than by humans. Unlike beliefs formed by a human mind, machine learning-generated beliefs are verifiable. This allows interventions to move beyond simple, belief-free designs like affirmative action, to more sophisticated ones, that constrain decision makers in ways that depend on what they are thinking. Such mind reading interventions can perform well where affirmative action does not, even when the beliefs being conditioned on are possibly incorrect and biased.

The dataset encompasses 897k images of wine labels and 824k reviews of wines curated from the Vivino platform. It has over 350k unique bottlings, annotated with year, region, rating, alcohol percentage, price, and grape composition. We obtained fine-grained flavor annotations on a subset by conducting a wine-tasting experiment with 256 participants who were asked to rank wines based on their similarity in flavor, resulting in more than 5k pairwise flavor distances. We propose a low-dimensional concept embedding algorithm that combines human experience with automatic machine similarity kernels. We demonstrate that this shared concept embedding space improves upon separate embedding spaces for coarse flavor classification (alcohol percentage, country, grape, price, rating) and aligns with the intricate human perception of flavor.

Rishi Sunak needs to decide whether he wants to back the UK's creative industries or gamble everything on an artificial intelligence boom, the chief executive of Getty Images has said. Craig Peters, who has led the image library since 2019, spoke out amid growing anger from the creative and media sector at the harvesting of their material for "training data" for AI companies. "When I look at the UK, probably about 10% of its GDP is sitting in the creative industries, whether that's movies, music, television. I think making that trade-off is risky. If I'm the UK, betting on AI, less than a quarter point of GDP within the UK today, significantly less than the creative industries, is a bit of a perplexing trade-off."

Despite the great success of large language models (LLMs) in various tasks, they suffer from generating hallucinations. We introduce Truth Forest, a method that enhances truthfulness in LLMs by uncovering hidden truth representations using multi-dimensional orthogonal probes. Specifically, it creates multiple orthogonal bases for modeling truth by incorporating orthogonal constraints into the probes. Moreover, we introduce Random Peek, a systematic technique considering an extended range of positions within the sequence, reducing the gap between discerning and generating truth features in LLMs. By employing this approach, we improved the truthfulness of Llama-2-7B from 40.8\% to 74.5\% on TruthfulQA. Likewise, significant improvements are observed in fine-tuned models. We conducted a thorough analysis of truth features using probes. Our visualization results show that orthogonal probes capture complementary truth-related features, forming well-defined clusters that reveal the inherent structure of the dataset.

The accelerating advancements in Artificial Intelligence (AI) and Machine Learning (ML), highlighted by the development of cutting-edge Generative Pre-trained Transformer (GPT) models by organizations such as OpenAI, Meta, and Anthropic, present new challenges and opportunities in warfare and security. Much of the current focus is on AI's integration within weapons systems and its role in rapid decision-making in kinetic conflict. However, an equally important but often overlooked aspect is the potential of AI-based psychological manipulation at internet scales within the information domain. These capabilities could pose significant threats to individuals, organizations, and societies globally. This paper explores the concept of AI weapons, their deployment, detection, and potential countermeasures.

As AI systems quickly improve in both breadth and depth of performance, they lend themselves to creating increasingly powerful and realistic agents, including the possibility of agents modeled on specific people. We anticipate that within our lifetimes it may become common practice for people to create a custom AI agent to interact with loved ones and/or the broader world after death. We call these generative ghosts, since such agents will be capable of generating novel content rather than merely parroting content produced by their creator while living. In this paper, we first discuss the design space of potential implementations of generative ghosts. We then discuss the practical and ethical implications of generative ghosts, including potential positive and negative impacts on individuals and society. Based on these considerations, we lay out a research agenda for the AI and HCI research communities to empower people to create and interact with AI afterlives in a safe and beneficial manner.

The advent of Generative AI, particularly through Large Language Models (LLMs) like ChatGPT and its successors, marks a paradigm shift in the AI landscape. Advanced LLMs exhibit multimodality, handling diverse data formats, thereby broadening their application scope. However, the complexity and emergent autonomy of these models introduce challenges in predictability and legal compliance. This paper delves into the legal and regulatory implications of Generative AI and LLMs in the European Union context, analyzing aspects of liability, privacy, intellectual property, and cybersecurity. It critically examines the adequacy of the existing and proposed EU legislation, including the Artificial Intelligence Act (AIA) draft, in addressing the unique challenges posed by Generative AI in general and LLMs in particular. The paper identifies potential gaps and shortcomings in the legislative framework and proposes recommendations to ensure the safe and compliant deployment of generative models, ensuring they align with the EU's evolving digital landscape and legal standards.

As Large Language Models and Natural Language Processing (NLP) technology rapidly develop and spread into daily life, it becomes crucial to anticipate how their use could harm people. One problem that has received a lot of attention in recent years is that this technology has displayed harmful biases, from generating derogatory stereotypes to producing disparate outcomes for different social groups. Although a lot of effort has been invested in assessing and mitigating these biases, our methods of measuring the biases of NLP models have serious problems and it is often unclear what they actually measure. In this paper, we provide an interdisciplinary approach to discussing the issue of NLP model bias by adopting the lens of psychometrics -- a field specialized in the measurement of concepts like bias that are not directly observable. In particular, we will explore two central notions from psychometrics, the construct validity and the reliability of measurement tools, and discuss how they can be applied in the context of measuring model bias. Our goal is to provide NLP practitioners with methodological tools for designing better bias measures, and to inspire them more generally to explore tools from psychometrics when working on bias measurement tools.

In an era characterized by the pervasive integration of artificial intelligence into decision-making processes across diverse industries, the demand for trust has never been more pronounced. This thesis embarks on a comprehensive exploration of bias and fairness, with a particular emphasis on their ramifications within the banking sector, where AI-driven decisions bear substantial societal consequences. In this context, the seamless integration of fairness, explainability, and human oversight is of utmost importance, culminating in the establishment of what is commonly referred to as "Responsible AI". This emphasizes the critical nature of addressing biases within the development of a corporate culture that aligns seamlessly with both AI regulations and universal human rights standards, particularly in the realm of automated decision-making systems. Nowadays, embedding ethical principles into the development, training, and deployment of AI models is crucial for compliance with forthcoming European regulations and for promoting societal good. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. These contributions are validated through their practical application in real-world scenarios, in collaboration with Intesa Sanpaolo. This collaborative effort not only contributes to our understanding of fairness but also provides practical tools for the responsible implementation of AI-based decision-making systems. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages, further promoting progress in the field of AI fairness.