As large language models (LLMs) are increasingly applied in areas influencing societal outcomes, it is critical to understand their tendency to perpetuate and amplify biases. This study investigates whether LLMs exhibit biases in predicting human mobility -- a fundamental human behavior -- based on race and gender. Using three prominent LLMs -- GPT-4, Gemini, and Claude -- we analyzed their predictions of visitations to points of interest (POIs) for individuals, relying on prompts that included names with and without explicit demographic details. We find that LLMs frequently reflect and amplify existing societal biases. Specifically, predictions for minority groups were disproportionately skewed, with these individuals being significantly less likely to be associated with wealth-related points of interest (POIs). Gender biases were also evident, as female individuals were consistently linked to fewer career-related POIs compared to their male counterparts. These biased associations suggest that LLMs not only mirror but also exacerbate societal stereotypes, particularly in contexts involving race and gender.

Background: Robot-assisted surgery has been widely adopted in recent years. However, compared to other health technologies operating in close proximity to patients in a vulnerable state, ethical issues of robot-assisted surgery have received less attention. Against the background of increasing automation that are expected to raise new ethical issues, this systematic review aims to map the state of the ethical debate in this field. Methods: A protocol was registered in the international prospective register of systematic reviews (PROSPERO CRD42023397951). Medline via PubMed, EMBASE, CINHAL, Philosophers' Index, IEEE Xplorer, Web of Science (Core Collection), Scopus and Google Scholar were searched in January 2023. Screening, extraction, and analysis were conducted independently by two authors. A qualitative narrative synthesis was performed. Results: Out of 1,723 records, 66 records were included in the final dataset. Seven major strands of the ethical debate emerged during analysis. These include questions of harms and benefits, responsibility and control, professional-patient relationship, ethical issues in surgical training and learning, justice, translational questions, and economic considerations. Discussion: The identified themes testify to a broad range of different and differing ethical issues requiring careful deliberation and integration into the surgical ethos. Looking forward, we argue that a different perspective in addressing robotic surgical devices might be helpful to consider upcoming challenges of automation.

LLMs are increasingly fine-tuned using RLHF datasets to align them with human preferences and values. However, very limited research has investigated which specific human values are operationalized through these datasets. In this paper, we introduce Value Imprint, a framework for auditing and classifying the human values embedded within RLHF datasets. To investigate the viability of this framework, we conducted three case study experiments by auditing the Anthropic/hh-rlhf, OpenAI WebGPT Comparisons, and Alpaca GPT-4-LLM datasets to examine the human values embedded within them. Our analysis involved a two-phase process. During the first phase, we developed a taxonomy of human values through an integrated review of prior works from philosophy, axiology, and ethics. Then, we applied this taxonomy to annotate 6,501 RLHF preferences. During the second phase, we employed the labels generated from the annotation as ground truth data for training a transformer-based machine learning model to audit and classify the three RLHF datasets. Through this approach, we discovered that information-utility values, including Wisdom/Knowledge and Information Seeking, were the most dominant human values within all three RLHF datasets. In contrast, prosocial and democratic values, including Well-being, Justice, and Human/Animal Rights, were the least represented human values. These findings have significant implications for developing language models that align with societal values and norms. We contribute our datasets to support further research in this area.

In order to address issues with manual vote counting during election procedures, this study intends to examine the viability of using advanced image processing techniques for automated voter counting. The study aims to shed light on how automated systems that utilize cutting-edge technologies like OpenCV, CVZone, and the MOG2 algorithm could greatly increase the effectiveness and openness of electoral operations. The empirical findings demonstrate how automated voter counting can enhance voting processes and rebuild public confidence in election outcomes, particularly in places where trust is low. The study also emphasizes how rigorous metrics, such as the F1 score, should be used to systematically compare the accuracy of automated systems against manual counting methods. This methodology enables a detailed comprehension of the differences in performance between automated and human counting techniques by providing a nuanced assessment. The incorporation of said measures serves to reinforce an extensive assessment structure, guaranteeing the legitimacy and dependability of automated voting systems inside the electoral sphere.

Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive performance of the embeddings when used in downstream tasks. While various techniques have been proposed \cite{bolukbasi2016man, zhao2018learning} and criticized\cite{gonen2019lipstick} for static embeddings, very little work has focused on mitigating bias in contextual embeddings. In this paper, we propose a novel objective function for MLM(Masked-Language Modeling) which largely mitigates the gender bias in contextual embeddings and also preserves the performance for downstream tasks. Since previous works on measuring bias in contextual embeddings lack in normative reasoning, we also propose novel evaluation metrics that are straight-forward and aligned with our motivations in debiasing. We also propose new methods for debiasing static embeddings and provide empirical proof via extensive analysis and experiments, as to why the main source of bias in static embeddings stems from the presence of stereotypical names rather than gendered words themselves. All experiments and embeddings studied are in English, unless otherwise specified.\citep{bender2011achieving}.

Molecular optimization, which aims to discover improved molecules from a vast chemical search space, is a critical step in chemical development. Various artificial intelligence technologies have demonstrated high effectiveness and efficiency on molecular optimization tasks. However, few of these technologies focus on balancing property optimization with constraint satisfaction, making it difficult to obtain high-quality molecules that not only possess desirable properties but also meet various constraints. To address this issue, we propose a constrained multi-property molecular optimization framework (CMOMO), which is a flexible and efficient method to simultaneously optimize multiple molecular properties while satisfying several drug-like constraints. CMOMO improves multiple properties of molecules with constraints based on dynamic cooperative optimization, which dynamically handles the constraints across various scenarios. Besides, CMOMO evaluates multiple properties within discrete chemical spaces cooperatively with the evolution of molecules within an implicit molecular space to guide the evolutionary search. Experimental results show the superior performance of the proposed CMOMO over five state-of-the-art molecular optimization methods on two benchmark tasks of simultaneously optimizing multiple non-biological activity properties while satisfying two structural constraints. Furthermore, the practical applicability of CMOMO is verified on two practical tasks, where it identified a collection of candidate ligands of $\beta$2-adrenoceptor GPCR and candidate inhibitors of glycogen synthase kinase-3$\beta$ with high properties and under drug-like constraints.

Abstract-- We present an approach for retartgeting off-theshelf Virtual Reality (VR) trackers to effectively teleoperate an upper-body humanoid while ensuring self-collision-free motions. Key to the effectiveness was the proper assignment of trackers to joint sets via modified task Jacobians and relaxed barrier functions for self-collision avoidance. The approach was validated on Apptronik's Astro hardware by demonstrating manipulation capabilities on a table-top environment with pickand-place box packing and a two-handed box pick up and handover task. I. INTRODUCTION Despite advances in robot autonomy, teleoperation [1], [2], [3] remains a practical approach for remote surveying Four 6 DoF trackers (headset, left controller, right controller, waist tracker) and the set of joints they control on the robot. A core problem with direct teleoperation is retargeting human-to-robot movements, which is an active area of research Finally, during direct teleoperation, it can be burdening [9], [10], [11], [12], [13], [14].

Open-source large language models are becoming increasingly available and popular among researchers and practitioners. While significant progress has been made on open-weight models, open training data is a practice yet to be adopted by the leading open-weight models creators. At the same time, there researchers are working to make language models safer. We propose a data curation pipeline to reduce harmful outputs by models trained on public domain data. There are unique challenges to working with public domain data, as these sources differ from web text in both form and content. Many sources are historical documents and are the result of Optical Character Recognition (OCR). Consequently, current state-of-the-art approaches to toxicity filtering are often infeasible or inappropriate for open data models. In this paper, we introduce a new fully open-source pipeline for open-data toxicity filtering. Our contributions are threefold. We create a custom training dataset, ToxicCommons, which is composed of texts which have been classified across five different dimensions (racial/origin-based, gender/sex-based, religious, ability-based discrimination, and violence). We use this dataset to train a custom classifier, Celadon, that can be used to detect toxic content in open data more efficiently at a larger scale. Finally, we describe the balanced approach to content filtration that optimizes safety filtering with respect to the filtered data available for training.

Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs' susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker's LLM to disrupt their own operations (passive defense) or even compromise the attacker's machine (active defense). By deploying purposefully vulnerable decoy services to attract the attacker and using dynamic prompt injections for the attacker's LLM, Mantis can autonomously hack back the attacker. In our experiments, Mantis consistently achieved over 95% effectiveness against automated LLM-driven attacks. To foster further research and collaboration, Mantis is available as an open-source tool: https://github.com/pasquini-dario/project_mantis

Complex engineering systems are often subject to multiple failure modes. Developing a remaining useful life (RUL) prediction model that does not consider the failure mode causing degradation is likely to result in inaccurate predictions. However, distinguishing between causes of failure without manually inspecting the system is nontrivial. This challenge is increased when the causes of historically observed failures are unknown. Sensors, which are useful for monitoring the state-of-health of systems, can also be used for distinguishing between multiple failure modes as the presence of multiple failure modes results in discriminatory behavior of the sensor signals. When systems are equipped with multiple sensors, some sensors may exhibit behavior correlated with degradation, while other sensors do not. Furthermore, which sensors exhibit this behavior may differ for each failure mode. In this paper, we present a simultaneous clustering and sensor selection approach for unlabeled training datasets of systems exhibiting multiple failure modes. The cluster assignments and the selected sensors are then utilized in real-time to first diagnose the active failure mode and then to predict the system RUL. We validate the complete pipeline of the methodology using a simulated dataset of systems exhibiting two failure modes and on a turbofan degradation dataset from NASA.