Financial decision-making hinges on the analysis of relevant information embedded in the enormous volume of documents in the financial domain. To address this challenge, we developed FinQAPT, an end-to-end pipeline that streamlines the identification of relevant financial reports based on a query, extracts pertinent context, and leverages Large Language Models (LLMs) to perform downstream tasks. To evaluate the pipeline, we experimented with various techniques to optimize the performance of each module using the FinQA dataset. We introduced a novel clustering-based negative sampling technique to enhance context extraction and a novel prompting method called Dynamic N-shot Prompting to boost the numerical question-answering capabilities of LLMs. At the module level, we achieved state-of-the-art accuracy on FinQA, attaining an accuracy of 80.6%. However, at the pipeline level, we observed decreased performance due to challenges in extracting relevant context from financial reports. We conducted a detailed error analysis of each module and the end-to-end pipeline, pinpointing specific challenges that must be addressed to develop a robust solution for handling complex financial tasks.

The challenge of finding content that aligns with users' interests within this abundance has become increasingly important. Recommender systems play a crucial role in addressing this issue, as they have the potential to provide precise recommendations that enhance user experience and save time in commercial applications [1]. These systems predict user ratings for specific items by employing data mining techniques and related predictive algorithms to make highly relevant predictions. By analyzing user historical behavior, preferences, and item characteristics, recommender systems effectively solve the information filtering problem by automatically matching items that may be of interest to users. Traditional recommender systems primarily consist of collaborative filtering [2], content-based recommendations [3], and hybrid recommendation methods, among which collaborative filtering is one of the earliest and most widely used techniques for recommending products or items based on past purchasing history.

Hosted by Ben Byford, The Machine Ethics Podcast brings together interviews with academics, authors, business leaders, designers and engineers on the subject of autonomous algorithms, artificial intelligence, machine learning, and technology's impact on society. This episode we're chatting with Alex Shvartsman about our AI future, human crafted storytelling, the generative AI use backlash, disclaimers for generated text, human vs AI authorship, practical or functional goals of LLMs, changing themes in science fiction, a diversity of international perspectives and more… Alex Shvartsman resides in Brooklyn, New York, and is the author of Kakistocracy (2023), The Middling Affliction (2022), and Eridani's Crown (2019) fantasy novels. Over 120 of his stories have appeared in Analog, Nature, Strange Horizons, etc. He won the WSFA Small Press Award for Short Fiction and was a three-time finalist for the Canopus Award for Excellence in Interstellar Fiction. His translations from Russian have appeared in F&SF, Clarkesworld, Tor.com, Analog, Asimov's, etc. Alex has edited over a dozen anthologies, including the long-running Unidentified Funny Objects series.

The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and generalize intricate patterns hidden in massive datasets. Modern learning models, while powerful, often exhibit a level of complexity that renders them opaque black boxes, resulting in a notable lack of transparency that hinders our ability to decipher their decision-making processes. Opacity challenges the interpretability and practical application of machine learning, especially in critical domains where understanding the underlying reasons is essential for informed decision-making. Explainable Artificial Intelligence (XAI) rises to meet that challenge, unraveling the complexity of black boxes by providing elucidating explanations. Among the various XAI approaches, feature attribution/importance XAI stands out for its capacity to delineate the significance of input features in the prediction process. However, most existing attribution methods have limitations, such as instability, when divergent explanations may result from similar or even the same instance. In this work, we introduce T-Explainer, a novel local additive attribution explainer based on Taylor expansion endowed with desirable properties, such as local accuracy and consistency, while stable over multiple runs. We demonstrate T-Explainer's effectiveness through benchmark experiments with well-known attribution methods. In addition, T-Explainer is developed as a comprehensive XAI framework comprising quantitative metrics to assess and visualize attribution explanations.

The field of neuroscience and the development of artificial neural networks (ANNs) have mutually influenced each other, drawing from and contributing to many concepts initially developed in statistical mechanics. Notably, Hopfield networks and Boltzmann machines are versions of the Ising model, a model extensively studied in statistical mechanics for over a century. In the first part of this chapter, we provide an overview of the principles, models, and applications of ANNs, highlighting their connections to statistical mechanics and statistical learning theory. Artificial neural networks can be seen as high-dimensional mathematical functions, and understanding the geometric properties of their loss landscapes (i.e., the high-dimensional space on which one wishes to find extrema or saddles) can provide valuable insights into their optimization behavior, generalization abilities, and overall performance. Visualizing these functions can help us design better optimization methods and improve their generalization abilities. Thus, the second part of this chapter focuses on quantifying geometric properties and visualizing loss functions associated with deep ANNs.

Shared control allows the human driver to collaborate with an assistive driving system while retaining the ability to make decisions and take control if necessary. However, human-vehicle teaming and planning are challenging due to environmental uncertainties, the human's bounded rationality, and the variability in human behaviors. An effective collaboration plan needs to learn and adapt to these uncertainties. To this end, we develop a Stackelberg meta-learning algorithm to create automated learning-based planning for shared control. The Stackelberg games are used to capture the leader-follower structure in the asymmetric interactions between the human driver and the assistive driving system. The meta-learning algorithm generates a common behavioral model, which is capable of fast adaptation using a small amount of driving data to assist optimal decision-making. We use a case study of an obstacle avoidance driving scenario to corroborate that the adapted human behavioral model can successfully assist the human driver in reaching the target destination. Besides, it saves driving time compared with a driver-only scheme and is also robust to drivers' bounded rationality and errors.

We present the CheckforAI text classifier, a transformer-based neural network trained to distinguish text written by large language models from text written by humans. CheckforAI outperforms zero-shot methods such as DetectGPT as well as leading commercial AI detection tools with over 9 times lower error rates on a comprehensive benchmark comprised of ten text domains (student writing, creative writing, scientific writing, books, encyclopedias, news, email, scientific papers, short-form Q&A) and 8 open- and closed-source large language models. We propose a training algorithm, hard negative mining with synthetic mirrors, that enables our classifier to achieve orders of magnitude lower false positive rates on high-data domains such as reviews. Finally, we show that CheckforAI is not biased against nonnative English speakers and generalizes to domains and models unseen during training.

Control barrier functions (CBFs) provide a simple yet effective way for safe control synthesis. Recently, work has been done using differentiable optimization (diffOpt) based methods to systematically construct CBFs for static obstacle avoidance tasks between geometric shapes. In this work, we extend the application of diffOpt CBFs to perform dynamic obstacle avoidance tasks. We show that by using the time-varying CBF (TVCBF) formulation, we can perform obstacle avoidance for dynamic geometric obstacles. Additionally, we show how to extend the TVCBF constraint to consider measurement noise and actuation limits. To demonstrate the efficacy of our proposed approach, we first compare its performance with a model predictive control based method and a circular CBF based method on a simulated dynamic obstacle avoidance task. Then, we demonstrate the performance of our proposed approach in experimental studies using a 7-degree-of-freedom Franka Research 3 robotic manipulator.

Large language models (LLMs) can store a vast amount of world knowledge, often extractable via question-answering (e.g., "What is Abraham Lincoln's birthday?"). However, do they answer such questions based on exposure to similar questions during training (i.e., cheating), or by genuinely learning to extract knowledge from sources like Wikipedia? In this paper, we investigate this issue using a controlled biography dataset. We find a strong correlation between the model's ability to extract knowledge and various diversity measures of the training data. $\textbf{Essentially}$, for knowledge to be reliably extracted, it must be sufficiently augmented (e.g., through paraphrasing, sentence shuffling) $\textit{during pretraining}$. Without such augmentation, knowledge may be memorized but not extractable, leading to 0% accuracy, regardless of subsequent instruction fine-tuning. To understand why this occurs, we employ (nearly) linear probing to demonstrate a strong connection between the observed correlation and how the model internally encodes knowledge -- whether it is linearly encoded in the hidden embeddings of entity names or distributed across other token embeddings in the training text. This paper provides $\textbf{several key recommendations for LLM pretraining in the industry}$: (1) rewrite the pretraining data -- using small, auxiliary models -- to provide knowledge augmentation, and (2) incorporate more instruction-finetuning data into the pretraining stage before it becomes too late.

Large language models (LLMs) have triggered tremendous success to empower our daily life by generative information. The personalization of LLMs could further contribute to their applications due to better alignment with human intents. Towards personalized generative services, a collaborative cloud-edge methodology is promising, as it facilitates the effective orchestration of heterogeneous distributed communication and computing resources. In this article, we put forward NetGPT to capably synergize appropriate LLMs at the edge and the cloud based on their computing capacity. In addition, edge LLMs could efficiently leverage location-based information for personalized prompt completion, thus benefiting the interaction with the cloud LLM. In particular, we present the feasibility of NetGPT by leveraging low-rank adaptation-based fine-tuning of open-source LLMs (i.e., GPT-2-base model and LLaMA model), and conduct comprehensive numerical comparisons with alternative cloud-edge collaboration or cloud-only techniques, so as to demonstrate the superiority of NetGPT. Subsequently, we highlight the essential changes required for an artificial intelligence (AI)-native network architecture towards NetGPT, with emphasis on deeper integration of communications and computing resources and careful calibration of logical AI workflow. Furthermore, we demonstrate several benefits of NetGPT, which come as by-products, as the edge LLMs' capability to predict trends and infer intents promises a unified solution for intelligent network management & orchestration. We argue that NetGPT is a promising AI-native network architecture for provisioning beyond personalized generative services.