We examine ProcessGPT, an AI model designed to automate, augment, and improve business processes, to study the challenges of managing business processes within the cognitive limitations of the human workforce, particularly individuals with cognitive disabilities. ProcessGPT provides a blueprint for designing efficient business processes that take into account human cognitive limitations. By viewing this through the lens of cognitive disabilities, we show that ProcessGPT improves process usability for individuals with and without cognitive disabilities. We also demonstrate that organizations implementing ProcessGPT-like capabilities will realize increased productivity, morale, and inclusion.

Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, provides us with a way to protect private data after training. Although several methods exist for such unlearning, it is unclear to what extent they result in models equivalent to those where the data to be forgotten was never learned in the first place. To address this challenge, we present TOFU, a Task of Fictitious Unlearning, as a benchmark aimed at helping deepen our understanding of unlearning. We offer a dataset of 200 diverse synthetic author profiles, each consisting of 20 question-answer pairs, and a subset of these profiles called the forget set that serves as the target for unlearning. We compile a suite of metrics that work together to provide a holistic picture of unlearning efficacy. Finally, we provide a set of baseline results from existing unlearning algorithms. Importantly, none of the baselines we consider show effective unlearning motivating continued efforts to develop approaches for unlearning that effectively tune models so that they truly behave as if they were never trained on the forget data at all.

Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this problem, Independent Component Analysis (ICA) is identified as an effective solution. ICA-transformed word embeddings reveal interpretable semantic axes; however, the order of these axes are arbitrary. In this study, we focus on this property and propose a novel method, Axis Tour, which optimizes the order of the axes. Inspired by Word Tour, a onedimensional word embedding method, we aim to improve the clarity of the word embedding space by maximizing the semantic continuity of the axes. Furthermore, we show through experiments Figure 1: Scatterplots of normalized ICA-transformed on downstream tasks that Axis Tour word embeddings whose axes are ordered by Axis Tour constructs better low-dimensional embeddings and Skewness Sort. In the upper part, Axis Tour is applied compared to both PCA and ICA.

Large language models (LLMs) have drastically changed the possible ways to design intelligent systems, shifting the focuses from massive data acquisition and new modeling training to human alignment and strategical elicitation of the full potential of existing pre-trained models. This paradigm shift, however, is not fully realized in financial sentiment analysis (FSA), due to the discriminative nature of this task and a lack of prescriptive knowledge of how to leverage generative models in such a context. This study investigates the effectiveness of the new paradigm, i.e., using LLMs without fine-tuning for FSA. Rooted in Minsky's theory of mind and emotions, a design framework with heterogeneous LLM agents is proposed. The framework instantiates specialized agents using prior domain knowledge of the types of FSA errors and reasons on the aggregated agent discussions. Comprehensive evaluation on FSA datasets show that the framework yields better accuracies, especially when the discussions are substantial. This study contributes to the design foundations and paves new avenues for LLMs-based FSA. Implications on business and management are also discussed.

Large language models (LLMs) have strong capabilities in solving diverse natural language processing tasks. However, the safety and security issues of LLM systems have become the major obstacle to their widespread application. Many studies have extensively investigated risks in LLM systems and developed the corresponding mitigation strategies. Leading-edge enterprises such as OpenAI, Google, Meta, and Anthropic have also made lots of efforts on responsible LLMs. Therefore, there is a growing need to organize the existing studies and establish comprehensive taxonomies for the community. In this paper, we delve into four essential modules of an LLM system, including an input module for receiving prompts, a language model trained on extensive corpora, a toolchain module for development and deployment, and an output module for exporting LLM-generated content. Based on this, we propose a comprehensive taxonomy, which systematically analyzes potential risks associated with each module of an LLM system and discusses the corresponding mitigation strategies. Furthermore, we review prevalent benchmarks, aiming to facilitate the risk assessment of LLM systems. We hope that this paper can help LLM participants embrace a systematic perspective to build their responsible LLM systems.

We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind. We demonstrate that EarthPT is an effective forecaster that can accurately predict future pixel-level surface reflectances across the 400-2300 nm range well into the future. For example, forecasts of the evolution of the Normalised Difference Vegetation Index (NDVI) have a typical error of approximately 0.05 (over a natural range of -1 -> 1) at the pixel level over a five month test set horizon, out-performing simple phase-folded models based on historical averaging. We also demonstrate that embeddings learnt by EarthPT hold semantically meaningful information and could be exploited for downstream tasks such as highly granular, dynamic land use classification. Excitingly, we note that the abundance of EO data provides us with -- in theory -- quadrillions of training tokens. Therefore, if we assume that EarthPT follows neural scaling laws akin to those derived for Large Language Models (LLMs), there is currently no data-imposed limit to scaling EarthPT and other similar `Large Observation Models.'

Do AI companies need to pay for the training data that powers their generative AI systems? The question is hotly contested in Silicon Valley and in a wave of lawsuits levied against tech behemoths like Meta, Google, and OpenAI. In Washington, DC, though, there seems to be a growing consensus that the tech giants need to cough up. Today, at a Senate hearing on AI's impact on journalism, lawmakers from both sides of the aisle agreed that OpenAI and others should pay media outlets for using their work in AI projects. "It's not only morally right," said Richard Blumenthal, the Democrat who chairs the Judiciary Subcommittee on Privacy, Technology, and the Law that held the hearing.

An alleged cartel drone attack in a remote community in the southern Mexican state of Guerrero killed 5 people, the Guerrero state prosecutor's office said. In a translated press release, the Guerrero state prosecutor's office said that the cartel attacked at least 30 people in the remote Mexican village that is plagued by cartel violence. Officials confirmed that five people were burned to death in a January 4 attack. "Through the Ministerial Investigative Police, on January 5, 2024, the first field investigations were conducted," the translated press release said. "Authorities found charred bone remains corresponding to 5 people from a burned vehicle."

If you squint and tilt your head, you can see some similarities in the blurry shapes that are Harvard and OpenAI. Each is a leading institution for building minds, whether real or artificial--Harvard educates smart humans, while OpenAI engineers smart machines--and each has been forced in recent days to stare down a common allegation. Namely, that they are represented by intellectual thieves. Last month, the conservative activist Christopher Rufo and the journalist Christopher Brunet accused then–Harvard President Claudine Gay of having copied short passages without attribution in her dissertation. Gay later admitted to "instances in my academic writings where some material duplicated other scholars' language, without proper attribution," for which she requested corrections. The two cases share common ground, yet many of the responses to them could not be more different.

OpenAI on Wednesday launched its GPT Store, a marketplace where paid ChatGPT users can buy and sell specialized chatbot agents based on the company's language models. The company, whose wildly popular product ChatGPT helped kickstart the boom in AI, already offers customized bots through its paid ChatGPT Plus service. The new store will allow users to offer and monetize a broader range of tools. Through the new models, chatbot agents could be developed with their own personalities or themes, including models for salary negotiating, creating lesson plans and developing recipes. The store has been compared with Apple's App store, fostering new development in the AI space from a wider range of users. Meta offers chatbots with differing personalities in a similar offering.