Large language models (LLMs) hold immense promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. In this work, we present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions and then conduct an empirical case study with Med-PaLM 2, resulting in the largest human evaluation study in this area to date. Our contributions include a multifactorial framework for human assessment of LLM-generated answers for biases, and EquityMedQA, a collection of seven newly-released datasets comprising both manually-curated and LLM-generated questions enriched for adversarial queries. Both our human assessment framework and dataset design process are grounded in an iterative participatory approach and review of possible biases in Med-PaLM 2 answers to adversarial queries. Through our empirical study, we find that the use of a collection of datasets curated through a variety of methodologies, coupled with a thorough evaluation protocol that leverages multiple assessment rubric designs and diverse rater groups, surfaces biases that may be missed via narrower evaluation approaches. Our experience underscores the importance of using diverse assessment methodologies and involving raters of varying backgrounds and expertise. We emphasize that while our framework can identify specific forms of bias, it is not sufficient to holistically assess whether the deployment of an AI system promotes equitable health outcomes. We hope the broader community leverages and builds on these tools and methods towards realizing a shared goal of LLMs that promote accessible and equitable healthcare for all.

Named Entity Recognition (NER) is a Natural Language Processing technique for extracting information from textual documents. However, much of the existing research on NER has been centered around English-language documents, leaving a gap in the availability of datasets tailored to the financial domain in Portuguese. This study addresses the need for NER within the financial domain, focusing on Portuguese-language texts extracted from earnings call transcriptions of Brazilian banks. By curating a comprehensive dataset comprising 384 transcriptions and leveraging weak supervision techniques for annotation, we evaluate the performance of monolingual models trained on Portuguese (BERTimbau and PTT5) and multilingual models (mBERT and mT5). Notably, we introduce a novel approach that reframes the token classification task as a text generation problem, enabling fine-tuning and evaluation of T5 models. Following the fine-tuning of the models, we conduct an evaluation on the test dataset, employing performance and error metrics. Our findings reveal that BERT-based models consistently outperform T5-based models. Furthermore, while the multilingual models exhibit comparable macro F1-scores, BERTimbau demonstrates superior performance over PTT5. A manual analysis of sentences generated by PTT5 and mT5 unveils a degree of similarity ranging from 0.89 to 1.0, between the original and generated sentences. However, critical errors emerge as both models exhibit discrepancies, such as alterations to monetary and percentage values, underscoring the importance of accuracy and consistency in the financial domain. Despite these challenges, PTT5 and mT5 achieve impressive macro F1-scores of 98.52% and 98.85%, respectively, with our proposed approach. Furthermore, our study sheds light on notable disparities in memory and time consumption for inference across the models.

Robots can serve as safety catalysts on construction job sites by taking over hazardous and repetitive tasks while alleviating the risks associated with existing manual workflows. Research on the safety of physical human-robot interaction (pHRI) is traditionally focused on addressing the risks associated with potential collisions. However, it is equally important to ensure that the workflows involving a collaborative robot are inherently safe, even though they may not result in an accident. For example, pHRI may require the human counterpart to use non-ergonomic body postures to conform to the robot hardware and physical configurations. Frequent and long-term exposure to such situations may result in chronic health issues. Safety and ergonomics assessment measures can be understood by robots if they are presented in algorithmic fashions so optimization for body postures is attainable. While frameworks such as Rapid Entire Body Assessment (REBA) have been an industry standard for many decades, they lack a rigorous mathematical structure which poses challenges in using them immediately for pHRI safety optimization purposes. Furthermore, learnable approaches have limited robustness outside of their training data, reducing generalizability. In this paper, we propose a novel framework that approaches optimization through Reinforcement Learning, ensuring precise, online ergonomic scores as compared to approximations, while being able to generalize and tune the regiment to any human and any task. To ensure practicality, the training is done in virtual reality utilizing Inverse Kinematics to simulate human movement mechanics. Experimental findings are compared to ergonomically naive object handover heuristics and indicate promising results where the developed framework can find the optimal object handover coordinates in pHRI contexts for manual material handling exemplary situations.

In the rapidly evolving field of artificial intelligence (AI), the application of large language models (LLMs) in agriculture, particularly in pest management, remains nascent. We aimed to prove the feasibility by evaluating the content of the pest management advice generated by LLMs, including the Generative Pre-trained Transformer (GPT) series from OpenAI and the FLAN series from Google. Considering the context-specific properties of agricultural advice, automatically measuring or quantifying the quality of text generated by LLMs becomes a significant challenge. We proposed an innovative approach, using GPT-4 as an evaluator, to score the generated content on Coherence, Logical Consistency, Fluency, Relevance, Comprehensibility, and Exhaustiveness. Additionally, we integrated an expert system based on crop threshold data as a baseline to obtain scores for Factual Accuracy on whether pests found in crop fields should take management action. Each model's score was weighted by percentage to obtain a final score. The results showed that GPT-3.4 and GPT-4 outperform the FLAN models in most evaluation categories. Furthermore, the use of instruction-based prompting containing domain-specific knowledge proved the feasibility of LLMs as an effective tool in agriculture, with an accuracy rate of 72%, demonstrating LLMs' effectiveness in providing pest management suggestions.

The rise of synoptic sky surveys has ushered in an era of big data in time-domain astronomy, making data science and machine learning essential tools for studying celestial objects. Tree-based (e.g. Random Forests) and deep learning models represent the current standard in the field. We explore the use of different distance metrics to aid in the classification of objects. For this, we developed a new distance metric based classifier called DistClassiPy. The direct use of distance metrics is an approach that has not been explored in time-domain astronomy, but distance-based methods can aid in increasing the interpretability of the classification result and decrease the computational costs. In particular, we classify light curves of variable stars by comparing the distances between objects of different classes. Using 18 distance metrics applied to a catalog of 6,000 variable stars in 10 classes, we demonstrate classification and dimensionality reduction. We show that this classifier meets state-of-the-art performance but has lower computational requirements and improved interpretability. We have made DistClassiPy open-source and accessible at https://pypi.org/project/distclassipy/ with the goal of broadening its applications to other classification scenarios within and beyond astronomy.

Predicting physical properties of materials from their crystal structures is a fundamental problem in materials science. In peripheral areas such as the prediction of molecular properties, fully connected attention networks have been shown to be successful. However, unlike these finite atom arrangements, crystal structures are infinitely repeating, periodic arrangements of atoms, whose fully connected attention results in infinitely connected attention. In this work, we show that this infinitely connected attention can lead to a computationally tractable formulation, interpreted as neural potential summation, that performs infinite interatomic potential summations in a deeply learned feature space. We then propose a simple yet effective Transformer-based encoder architecture for crystal structures called Crystalformer. Compared to an existing Transformer-based model, the proposed model requires only 29.4% of the number of parameters, with minimal modifications to the original Transformer architecture. Despite the architectural simplicity, the proposed method outperforms state-of-the-art methods for various property regression tasks on the Materials Project and JARVIS-DFT datasets.

A fundamental problem in decision-making systems is the presence of inequity across demographic lines. However, inequity can be difficult to quantify, particularly if our notion of equity relies on hard-to-measure notions like risk (e.g., equal access to treatment for those who would die without it). Auditing such inequity requires accurate measurements of individual risk, which is difficult to estimate in the realistic setting of unobserved confounding. In the case that these unobservables "explain" an apparent disparity, we may understate or overstate inequity. In this paper, we show that one can still give informative bounds on allocation rates among high-risk individuals, even while relaxing or (surprisingly) even when eliminating the assumption that all relevant risk factors are observed. We utilize the fact that in many real-world settings (e.g., the introduction of a novel treatment) we have data from a period prior to any allocation, to derive unbiased estimates of risk. We demonstrate the effectiveness of our framework on a real-world study of Paxlovid allocation to COVID-19 patients, finding that observed racial inequity cannot be explained by unobserved confounders of the same strength as important observed covariates.

Three-dimensional shape sensing in soft and continuum robotics is a crucial aspect for stable actuation and control in fields such as Minimally Invasive surgery, as the estimation of complex curvatures while using continuum robotic tools is required to manipulate through fragile paths. This challenge has been addressed using a range of different sensing techniques, for example, Fibre Bragg grating (FBG) technology, inertial measurement unit (IMU) sensor networks or stretch sensors. Previously, an optics-based method, using optoelectronic sensors was explored, offering a simple and cost-effective solution for shape sensing in a flexible tendon-actuated manipulator in two orientations. This was based on proximity-modulated angle estimation and has been the basis for the shape-sensing method addressed in this paper. The improved and miniaturized technique demonstrated in this paper is based on the use of a spherically shaped reflector with optoelectronic sensors integrated into a tendon actuated robotic manipulator. Upgraded sensing capability is achieved using optimization of the spherical reflector shape in terms of sensor range and resolution, and improved calibration is achieved through the integration of spherical bearings for friction-free motion. Shape estimation is achieved in two orientations upon calibration of sensors, with a maximum Root Mean Square Error (RMS) of 3.37{\deg}.

The growing interest in developing smart diagnostic systems to help medical experts process extensive data for treating incurable diseases has been notable. In particular, the challenge of identifying thyroid cancer (TC) has seen progress with the use of machine learning (ML) and big data analysis, incorporating transformers to evaluate TC prognosis and determine the risk of malignancy in individuals. This review article presents a summary of various studies on AIbased approaches, especially those employing transformers, for diagnosing TC. It introduces a new categorization system for these methods based on artifcial intelligence (AI) algorithms, the goals of the framework, and the computing environments used. Additionally, it scrutinizes and contrasts the available TC datasets by their features. The paper highlights the importance of AI instruments in aiding the diagnosis and treatment of TC through supervised, unsupervised, or mixed approaches, with a special focus on the ongoing importance of transformers in medical diagnostics and disease management. It further discusses the progress made and the continuing obstacles in this area. Lastly, it explores future directions and focuses within this research feld.

This poses challenges for applications interested in targeting specific demographics (e.g., an African American business or NGO; a voice-tutoring system for children that are not of White ethnicity, etc.). The ultimate goal of the project described in this paper is to provide to designers, developers, and enterprises the choice of having a professional voice which is clearly recognizable as African American, and therefore more able to address diversity and inclusiveness issues. Being more precise, our goal is to create an African American Text-to-Speech system, which we will refer simply as an African American voice or AA voice, able to produce synthetic audio segments from standard English texts, and which will be recognized by African American speakers and non-speakers as sounding like a native African American speaker. The AA voice should exhibit a level of technical quality similar to the Standard American English (SAE) synthetic voices currently available through professional platforms. The evaluation of the technical quality of the AA voice, however, is not addressed in this paper, which focuses primarily on whether the AA voice can be recognized as sounding like an African American speaker. Linguists [27, 28] have described a continuum of dialects under what is often termed African American Vernacular English (AAVE). At one end of the spectrum, one finds the largest deviation from SAE in terms of lexicon (including slang), syntax and morphology, and phonological/phonetic properties. At the other end, AAVE speakers begin to approach SAE in terms of lexicon and grammar but still retain marked speech characteristics (primarily in terms of intonation, phonation, and vowel placement [14, 28]) which grant the speech a distinctive identity which listeners use as cues in the perception of African American English [44].