With increased availability of next-generation technology and data mining tools, insurance company use of external consumer data sets and artificial intelligence (AI) and machine learning (ML)-enabled analytical models is rapidly expanding and accelerating. Insurers have initially targeted key business areas such as underwriting, pricing, fraud detection, marketing distribution and claims management to leverage technical innovations to realize enhanced risk management, revenue growth and improved profitability. At the same time, regulators worldwide are intensifying their focus on the governance and fairness challenges presented by these complex, highly innovative tools – specifically, the potential for unintended bias against protected classes of people. In the United States, the Colorado Division of Insurance recently issued a first-in-the-nation draft regulation to support the implementation of a 2021 law passed by the state's legislature.1 This law (SB21-169) prohibits life insurers from using external personal data and information sources (ECDIS), or employing algorithms and models that use ECDIS, where the resulting impact of such use is unfair discrimination against consumers on the basis of race, color, national or ethnic origin, religion, sex, sexual orientation, disability, gender identity or gender expression.2

Making sense of familiar yet new situations typically involves making generalizations about causal schemas, stories that help humans reason about event sequences. Reasoning about events includes identifying cause and effect relations shared across event instances, a process we refer to as causal schema induction. Statistical schema induction systems may leverage structural knowledge encoded in discourse or the causal graphs associated with event meaning, however resources to study such causal structure are few in number and limited in size. In this work, we investigate how to apply schema induction models to the task of knowledge discovery for enhanced search of English-language news texts. To tackle the problem of data scarcity, we present Torquestra, a manually curated dataset of text-graph-schema units integrating temporal, event, and causal structures. We benchmark our dataset on three knowledge discovery tasks, building and evaluating models for each. Results show that systems that harness causal structure are effective at identifying texts sharing similar causal meaning components rather than relying on lexical cues alone. We make our dataset and models available for research purposes.

Existing foundation models are trained on copyrighted material. Deploying these models can pose both legal and ethical risks when data creators fail to receive appropriate attribution or compensation. In the United States and several other countries, copyrighted content may be used to build foundation models without incurring liability due to the fair use doctrine. However, there is a caveat: If the model produces output that is similar to copyrighted data, particularly in scenarios that affect the market of that data, fair use may no longer apply to the output of the model. In this work, we emphasize that fair use is not guaranteed, and additional work may be necessary to keep model development and deployment squarely in the realm of fair use. First, we survey the potential risks of developing and deploying foundation models based on copyrighted content. We review relevant U.S. case law, drawing parallels to existing and potential applications for generating text, source code, and visual art. Experiments confirm that popular foundation models can generate content considerably similar to copyrighted material. Second, we discuss technical mitigations that can help foundation models stay in line with fair use. We argue that more research is needed to align mitigation strategies with the current state of the law. Lastly, we suggest that the law and technical mitigations should co-evolve. For example, coupled with other policy mechanisms, the law could more explicitly consider safe harbors when strong technical tools are used to mitigate infringement harms. This co-evolution may help strike a balance between intellectual property and innovation, which speaks to the original goal of fair use. But we emphasize that the strategies we describe here are not a panacea and more work is needed to develop policies that address the potential harms of foundation models.

What are the events involved in a pandemic outbreak? What steps should be taken when planning a wedding? The answers to these questions can be found by collecting many documents on the complex event of interest, extracting relevant information, and analyzing it. We present a new approach in which large language models are utilized to generate source documents that allow predicting, given a high-level event definition, the specific events, arguments, and relations between them to construct a schema that describes the complex event in its entirety. Using our model, complete schemas on any topic can be generated on-the-fly without any manual data collection, i.e., in a zero-shot manner. Moreover, we develop efficient methods to extract pertinent information from texts and demonstrate in a series of experiments that these schemas are considered to be more complete than human-curated ones in the majority of examined scenarios. Finally, we show that this framework is comparable in performance with previous supervised schema induction methods that rely on collecting real texts while being more general and flexible without the need for a predefined ontology.

Algorithms and models are increasingly deployed to inform decisions about people, inevitably affecting their lives. As a consequence, those in charge of developing these models must carefully evaluate their impact on different groups of people and favour group fairness, that is, ensure that groups determined by sensitive demographic attributes, such as race or sex, are not treated unjustly. To achieve this goal, the availability (awareness) of these demographic attributes to those evaluating the impact of these models is fundamental. Unfortunately, collecting and storing these attributes is often in conflict with industry practices and legislation on data minimisation and privacy. For this reason, it can be hard to measure the group fairness of trained models, even from within the companies developing them. In this work, we tackle the problem of measuring group fairness under unawareness of sensitive attributes, by using techniques from quantification, a supervised learning task concerned with directly providing group-level prevalence estimates (rather than individual-level class labels). We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem, as they are robust to inevitable distribution shifts while at the same time decoupling the (desirable) objective of measuring group fairness from the (undesirable) side effect of allowing the inference of sensitive attributes of individuals. More in detail, we show that fairness under unawareness can be cast as a quantification problem and solved with proven methods from the quantification literature. We show that these methods outperform previous approaches to measure demographic parity in five experimental protocols, corresponding to important challenges that complicate the estimation of classifier fairness under unawareness.

Last week, I had the pleasure of interviewing Kevin Novak, founder of Rackhouse Venture Capital and Uber's first head of AI, and Alex Lee, founder and CEO, of Truewind, in front of a crowd of investors and LPs. The panel was titled, "AI and the battle to capture its value chain: base layer accrual vs the fine tuners." Here's a sample of the questions and topics we addressed. How has AI evolved since you started working in the field, and what is different about this current hype cycle compared to previous ones? According to the Economist, over 500 generative AI startups have collectively raised over $11B, not including OpenAI.

The recent surge in interest in new AI applications in 2023 has been nothing short of extraordinary. From ChatGPT to a growing list of other new apps, our technology and business worlds are rapidly evolving before our eyes in many exciting ways. As a curious technologist, I am fascinated by these new trends, and I wrote this primer on the topic back in January: "ChatGPT: Hopes, Dreams, Cheating and Cybersecurity." I have received many questions about the use of ChatGPT to generate content, and this YouTube video addressed the question: "Is It Plagiarism to Use ChatGPT in Your Published Works?" But as an author, blogger and creator of original content, I have other concerns that are growing just as fast as the new technology is being deployed.

Michael Scott, the protagonist from the US version of The Office, is using an AI recruiter to hire a receptionist. The text-based system asks applicants five questions that delve into how they responded to past work situations, including dealing with difficult colleagues and juggling competing work demands. Potential employees type their answers into a chat-style program that resembles a responsive help desk. The real – and unnerving – power of AI then kicks in, sending a score and traits profile to the employer, and a personality report to the applicant. This demonstration, by Melbourne-based startup Sapia.ai,

Meredith Broussard is a data journalist and academic whose research focuses on bias in artificial intelligence (AI). She has been in the vanguard of raising awareness and sounding the alarm about unchecked AI. Her previous book, Artificial Unintelligence (2018), coined the term "technochauvinism" to describe the blind belief in the superiority of tech solutions to solve our problems. She appeared in the Netflix documentary Coded Bias (2020), which explores how algorithms encode and propagate discrimination. Her new book is More Than a Glitch: Confronting Race, Gender and Ability Bias in Tech.

Robin used its own machine learning model that it had trained on proprietary data from 4.5m legal documents over time, combined with its 30 in-house lawyers that "supervise" the model and encourage it to suggest amends.