Spurious correlations were found to be an important factor explaining model performance in various NLP tasks (e.g., gender or racial artifacts), often considered to be ''shortcuts'' to the actual task. However, humans tend to similarly make quick (and sometimes wrong) predictions based on societal and cognitive presuppositions. In this work we address the question: can we quantify the extent to which model biases reflect human behaviour? Answering this question will help shed light on model performance and provide meaningful comparisons against humans. We approach this question through the lens of the dual-process theory for human decision-making. This theory differentiates between an automatic unconscious (and sometimes biased) ''fast system'' and a ''slow system'', which when triggered may revisit earlier automatic reactions. We make several observations from two crowdsourcing experiments of gender bias in coreference resolution, using self-paced reading to study the ''fast'' system, and question answering to study the ''slow'' system under a constrained time setting. On real-world data humans make $\sim$3\% more gender-biased decisions compared to models, while on synthetic data models are $\sim$12\% more biased.

An important aspect of developing LLMs that interact with humans is to align models' behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by Pew Research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling both user opinions as well as user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. In addition to the typical approach of prompting LLMs with demographics and ideology, we discover that utilizing the most relevant past opinions from individual users enables the model to predict user opinions more accurately.

Concerns regarding unfairness and discrimination in the context of artificial intelligence (AI) systems have recently received increased attention from both legal and computer science scholars. Yet, the degree of overlap between notions of algorithmic bias and fairness on the one hand, and legal notions of discrimination and equality on the other, is often unclear, leading to misunderstandings between computer science and law. What types of bias and unfairness does the law address when it prohibits discrimination? What role can fairness metrics play in establishing legal compliance? In this paper, we aim to illustrate to what extent European Union (EU) non-discrimination law coincides with notions of algorithmic fairness proposed in computer science literature and where they differ. The contributions of this paper are as follows. First, we analyse seminal examples of algorithmic unfairness through the lens of EU non-discrimination law, drawing parallels with EU case law. Second, we set out the normative underpinnings of fairness metrics and technical interventions and compare these to the legal reasoning of the Court of Justice of the EU. Specifically, we show how normative assumptions often remain implicit in both disciplinary approaches and explain the ensuing limitations of current AI practice and non-discrimination law. We conclude with implications for AI practitioners and regulators.

Relations such as "is influenced by", "is known for" or "is a competitor of" are inherently graded: we can rank entity pairs based on how well they satisfy these relations, but it is hard to draw a line between those pairs that satisfy them and those that do not. Such graded relations play a central role in many applications, yet they are typically not covered by existing Knowledge Graphs. In this paper, we consider the possibility of using Large Language Models (LLMs) to fill this gap. To this end, we introduce a new benchmark, in which entity pairs have to be ranked according to how much they satisfy a given graded relation. The task is formulated as a few-shot ranking problem, where models only have access to a description of the relation and five prototypical instances. We use the proposed benchmark to evaluate state-of-the-art relation embedding strategies as well as several recent LLMs, covering both publicly available LLMs and closed models such as GPT-4. Overall, we find a strong correlation between model size and performance, with smaller Language Models struggling to outperform a naive baseline. The results of the largest Flan-T5 and OPT models are remarkably strong, although a clear gap with human performance remains.

We identify two crucial limitations in the evaluation of recent parallel-integrated method Parallel Context Windows (PCW) (Ratner et al., 2023), which extends the maximum context lengths of language models, e.g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques. We first show that a simple yet strong baseline, weighted sum ensemble, is missing for the incontext few-shot classification. Moreover, on more challenging Chain-of-Thought (CoT) reasoning (e.g., HotpotQA), PCW would present unexpected deterioration regarding question miscomprehension and false inference. Based on our findings, we suggest that the existing PCW design may not guarantee sufficient improvement and practicality in handling lengthy documents in real-world applications. More community efforts on enabling language models' Figure 1: (a) PCW is comparable with Parallel Ensemble long context understanding ability should (PE) and outperforms on fine-grained classification be paid.

The new regulatory framework proposal on Artificial Intelligence (AI) published by the European Commission establishes a new risk-based legal approach. The proposal highlights the need to develop adequate risk assessments for the different uses of AI. This risk assessment should address, among others, the detection and mitigation of bias in AI. In this work we analyze statistical approaches to measure biases in automatic decision-making systems. We focus our experiments in face recognition technologies. We propose a novel way to measure the biases in machine learning models using a statistical approach based on the N-Sigma method. N-Sigma is a popular statistical approach used to validate hypotheses in general science such as physics and social areas and its application to machine learning is yet unexplored. In this work we study how to apply this methodology to develop new risk assessment frameworks based on bias analysis and we discuss the main advantages and drawbacks with respect to other popular statistical tests.

The adoption of data science brings vast benefits to Small and Medium-sized Enterprises (SMEs) including business productivity, economic growth, innovation and jobs creation. Data Science can support SMEs to optimise production processes, anticipate customers' needs, predict machinery failures and deliver efficient smart services. Businesses can also harness the power of Artificial Intelligence (AI) and Big Data and the smart use of digital technologies to enhance productivity and performance, paving the way for innovation. However, integrating data science decisions into an SME requires both skills and IT investments. In most cases, such expenses are beyond the means of SMEs due to limited resources and restricted access to financing. This paper presents trends and challenges towards an effective data-driven decision making for organisations based on a case study of 85 SMEs, mostly from the West Midlands region of England. The work is supported as part of a 3 years ERDF (European Regional Development Funded project) in the areas of big data management, analytics and business intelligence. We present two case studies that demonstrates the potential of Digitisation, AI and Machine Learning and use these as examples to unveil challenges and showcase the wealth of current available opportunities for SMEs.

With large Foundation Models (FMs), language technologies (AI in general) are entering a new paradigm: eliminating the need for developing large-scale task-specific datasets and supporting a variety of tasks through set-ups ranging from zero-shot to few-shot learning. However, understanding FMs capabilities requires a systematic benchmarking effort by comparing FMs performance with the state-of-the-art (SOTA) task-specific models. With that goal, past work focused on the English language and included a few efforts with multiple languages. Our study contributes to ongoing research by evaluating FMs performance for standard Arabic NLP and Speech processing, including a range of tasks from sequence tagging to content classification across diverse domains. We start with zero-shot learning using GPT-3.5-turbo, Whisper, and USM, addressing 33 unique tasks using 59 publicly available datasets resulting in 96 test setups. For a few tasks, FMs performs on par or exceeds the performance of the SOTA models but for the majority it under-performs. Given the importance of prompt for the FMs performance, we discuss our prompt strategies in detail and elaborate on our findings. Our future work on Arabic AI will explore few-shot prompting, expand the range of tasks, and investigate additional open-source models.

Tasks involving text generation based on multiple input texts, such as multi-document summarization, long-form question answering and contemporary dialogue applications, challenge models for their ability to properly consolidate partly-overlapping multi-text information. However, these tasks entangle the consolidation phase with the often subjective and ill-defined content selection requirement, impeding proper assessment of models' consolidation capabilities. In this paper, we suggest revisiting the sentence union generation task as an effective well-defined testbed for assessing text consolidation capabilities, decoupling the consolidation challenge from subjective content selection. To support research on this task, we present refined annotation methodology and tools for crowdsourcing sentence union, create the largest union dataset to date and provide an analysis of its rich coverage of various consolidation aspects. We then propose a comprehensive evaluation protocol for union generation, including both human and automatic evaluation. Finally, as baselines, we evaluate state-of-the-art language models on the task, along with a detailed analysis of their capacity to address multi-text consolidation challenges and their limitations.

Recent advancements in Machine Learning have sparked a wave of new possibilities and applications that could potentially transform various aspects of our daily lives and revolutionize numerous professions through automation. However, training such algorithms relies heavily on extensive content, either annotated or generated by individuals who may be impacted by these algorithms. Consequently, the identification and determination of when and how content can be used within this framework without infringing upon individuals' legal rights have become a pressing challenge.