Search

In response to the growing complexity and volume of scientific literature, this paper introduces the LLMs4Synthesis framework, designed to enhance the capabilities of Large Language Models (LLMs) in generating high-quality scientific syntheses. This framework addresses the need for rapid, coherent, and contextually rich integration of scientific insights, leveraging both open-source and proprietary LLMs. It also examines the effectiveness of LLMs in evaluating the integrity and reliability of these syntheses, alleviating inadequacies in current quantitative metrics. Our study contributes to this field by developing a novel methodology for processing scientific papers, defining new synthesis types, and establishing nine detailed quality criteria for evaluating syntheses. The integration of LLMs with reinforcement learning and AI feedback is proposed to optimize synthesis quality, ensuring alignment with established criteria. The LLMs4Synthesis framework and its components are made available, promising to enhance both the generation and evaluation processes in scientific research synthesis., Comment: 12 pages, 3 figures, Accepted to JCDL 2024 Research Track

Content-addressable memories such as Modern Hopfield Networks (MHN) have been studied as mathematical models of auto-association and storage/retrieval in the human declarative memory, yet their practical use for large-scale content storage faces challenges. Chief among them is the occurrence of meta-stable states, particularly when handling large amounts of high dimensional content. This paper introduces Hopfield Encoding Networks (HEN), a framework that integrates encoded neural representations into MHNs to improve pattern separability and reduce meta-stable states. We show that HEN can also be used for retrieval in the context of hetero association of images with natural language queries, thus removing the limitation of requiring access to partial content in the same domain. Experimental results demonstrate substantial reduction in meta-stable states and increased storage capacity while still enabling perfect recall of a significantly larger number of inputs advancing the practical utility of associative memory networks for real-world tasks., Comment: 17 pages, 8 figures, workshop submission to Neurips

In order to solve problems of practical importance, quantum computers will likely need to incorporate quantum error correction, where a logical qubit is redundantly encoded in many noisy physical qubits. The large physical-qubit overhead typically associated with error correction motivates the search for more hardware-efficient approaches. Here, using a microfabricated superconducting quantum circuit, we realize a logical qubit memory formed from the concatenation of encoded bosonic cat qubits with an outer repetition code of distance $d=5$. The bosonic cat qubits are passively protected against bit flips using a stabilizing circuit. Cat-qubit phase-flip errors are corrected by the repetition code which uses ancilla transmons for syndrome measurement. We realize a noise-biased CX gate which ensures bit-flip error suppression is maintained during error correction. We study the performance and scaling of the logical qubit memory, finding that the phase-flip correcting repetition code operates below threshold, with logical phase-flip error decreasing with code distance from $d=3$ to $d=5$. Concurrently, the logical bit-flip error is suppressed with increasing cat-qubit mean photon number. The minimum measured logical error per cycle is on average $1.75(2)\%$ for the distance-3 code sections, and $1.65(3)\%$ for the longer distance-5 code, demonstrating the effectiveness of bit-flip error suppression throughout the error correction cycle. These results, where the intrinsic error suppression of the bosonic encodings allows us to use a hardware-efficient outer error correcting code, indicate that concatenated bosonic codes are a compelling paradigm for reaching fault-tolerant quantum computation., Comment: Comments on the manuscript welcome!

This paper outlines the LLMs4OL 2024, the first edition of the Large Language Models for Ontology Learning Challenge. LLMs4OL is a community development initiative collocated with the 23rd International Semantic Web Conference (ISWC) to explore the potential of Large Language Models (LLMs) in Ontology Learning (OL), a vital process for enhancing the web with structured knowledge to improve interoperability. By leveraging LLMs, the challenge aims to advance understanding and innovation in OL, aligning with the goals of the Semantic Web to create a more intelligent and user-friendly web. In this paper, we give an overview of the 2024 edition of the LLMs4OL challenge and summarize the contributions., Comment: 15 pages, 1 figure, Will appear in "The 1st LLMs4OL Challenge @ ISWC 2024" proceedings

Diffusion-weighted imaging (DWI) is a type of Magnetic Resonance Imaging (MRI) technique sensitised to the diffusivity of water molecules, offering the capability to inspect tissue microstructures and is the only in-vivo method to reconstruct white matter fiber tracts non-invasively. The DWI signal can be analysed with the diffusion tensor imaging (DTI) model to estimate the directionality of water diffusion within voxels. Several scalar metrics, including axial diffusivity (AD), mean diffusivity (MD), radial diffusivity (RD), and fractional anisotropy (FA), can be further derived from DTI to quantitatively summarise the microstructural integrity of brain tissue. These scalar metrics have played an important role in understanding the organisation and health of brain tissue at a microscopic level in clinical studies. However, reliable DTI metrics rely on DWI acquisitions with high gradient directions, which often go beyond the commonly used clinical protocols. To enhance the utility of clinically acquired DWI and save scanning time for robust DTI analysis, this work proposes DirGeo-DTI, a deep learning-based method to estimate reliable DTI metrics even from a set of DWIs acquired with the minimum theoretical number (6) of gradient directions. DirGeo-DTI leverages directional encoding and geometric constraints to facilitate the training process. Two public DWI datasets were used for evaluation, demonstrating the effectiveness of the proposed method. Extensive experimental results show that the proposed method achieves the best performance compared to existing DTI enhancement methods and potentially reveals further clinical insights with routine clinical DWI scans., Comment: Accepted to ICONIP2024, Diffusion Weighted Imaging, Diffusion Tensor Imaging, Angular Resolution Enhancement, Fractional Anisotropy

The increasing amount of published scholarly articles, exceeding 2.5 million yearly, raises the challenge for researchers in following scientific progress. Integrating the contributions from scholarly articles into a novel type of cognitive knowledge graph (CKG) will be a crucial element for accessing and organizing scholarly knowledge, surpassing the insights provided by titles and abstracts. This research focuses on effectively conveying structured scholarly knowledge by utilizing large language models (LLMs) to categorize scholarly articles and describe their contributions in a structured and comparable manner. While previous studies explored language models within specific research domains, the extensive domain-independent knowledge captured by LLMs offers a substantial opportunity for generating structured contribution descriptions as CKGs. Additionally, LLMs offer customizable pathways through prompt engineering or fine-tuning, thus facilitating to leveraging of smaller LLMs known for their efficiency, cost-effectiveness, and environmental considerations. Our methodology involves harnessing LLM knowledge, and complementing it with domain expert-verified scholarly data sourced from a CKG. This strategic fusion significantly enhances LLM performance, especially in tasks like scholarly article categorization and predicate recommendation. Our method involves fine-tuning LLMs with CKG knowledge and additionally injecting knowledge from a CKG with a novel prompting technique significantly increasing the accuracy of scholarly knowledge extraction. We integrated our approach in the Open Research Knowledge Graph (ORKG), thus enabling precise access to organized scholarly knowledge, crucially benefiting domain-independent scholarly knowledge exchange and dissemination among policymakers, industrial practitioners, and the general public.

Smart TVs implement a unique tracking approach called Automatic Content Recognition (ACR) to profile viewing activity of their users. ACR is a Shazam-like technology that works by periodically capturing the content displayed on a TV's screen and matching it against a content library to detect what content is being displayed at any given point in time. While prior research has investigated third-party tracking in the smart TV ecosystem, it has not looked into second-party ACR tracking that is directly conducted by the smart TV platform. In this work, we conduct a black-box audit of ACR network traffic between ACR clients on the smart TV and ACR servers. We use our auditing approach to systematically investigate whether (1) ACR tracking is agnostic to how a user watches TV (e.g., linear vs. streaming vs. HDMI), (2) privacy controls offered by smart TVs have an impact on ACR tracking, and (3) there are any differences in ACR tracking between the UK and the US. We perform a series of experiments on two major smart TV platforms: Samsung and LG. Our results show that ACR works even when the smart TV is used as a "dumb" external display, opting-out stops network traffic to ACR servers, and there are differences in how ACR works across the UK and the US., Comment: In Proceedings of the 24th ACM Internet Measurement Conference (IMC) 2024

The use of synthetic data has played a critical role in recent state-of-art breakthroughs. However, overly relying on a single oracle teacher model to generate data has been shown to lead to model collapse and invite propagation of biases. These limitations are particularly evident in multilingual settings, where the absence of a universally effective teacher model that excels across all languages presents significant challenges. In this work, we address these extreme difference by introducing "multilingual arbitrage", which capitalizes on performance variations between multiple models for a given language. To do so, we strategically route samples through a diverse pool of models, each with unique strengths in different languages. Across exhaustive experiments on state-of-art models, our work suggests that arbitrage techniques allow for spectacular gains in performance that far outperform relying on a single teacher. In particular, compared to the best single teacher, we observe gains of up to 56.5% improvement in win rates averaged across all languages when switching to multilingual arbitrage. We observe the most significant gains for the least resourced languages in our pool.

This study demonstrates the application of instruction finetuning of pretrained Large Language Models (LLMs) to automate the generation of AI research leaderboards, extracting (Task, Dataset, Metric, Score) quadruples from articles. It aims to streamline the dissemination of advancements in AI research by transitioning from traditional, manual community curation, or otherwise taxonomy-constrained natural language inference (NLI) models, to an automated, generative LLM-based approach. Utilizing the FLAN-T5 model, this research enhances LLMs' adaptability and reliability in information extraction, offering a novel method for structured knowledge representation., Comment: arXiv admin note: text overlap with arXiv:2407.02409

Precisely estimating lumen boundaries in intravascular ultrasound (IVUS) is needed for sizing interventional stents to treat deep vein thrombosis (DVT). Unfortunately, current segmentation networks like the UNet lack the precision needed for clinical adoption in IVUS workflows. This arises due to the difficulty of automatically learning accurate lumen contour from limited training data while accounting for the radial geometry of IVUS imaging. We propose the Geo-UNet framework to address these issues via a design informed by the geometry of the lumen contour segmentation task. We first convert the input data and segmentation targets from Cartesian to polar coordinates. Starting from a convUNet feature extractor, we propose a two-task setup, one for conventional pixel-wise labeling and the other for single boundary lumen-contour localization. We directly combine the two predictions by passing the predicted lumen contour through a new activation (named CDFeLU) to filter out spurious pixel-wise predictions. Our unified loss function carefully balances area-based, distance-based, and contour-based penalties to provide near clinical-grade generalization in unseen patient data. We also introduce a lightweight, inference-time technique to enhance segmentation smoothness. The efficacy of our framework on a venous IVUS dataset is shown against state-of-the-art models., Comment: Accepted into the 15th workshop on Machine Learning in Medical Imaging at MICCAI 2024. (* indicates equal contribution)

Mergers of and interactions between galaxies imprint a wide diversity of morphological, dynamical, and chemical characteristics in stellar halos and tidal streams. Measuring these characteristics elucidates aspects of the progenitors of the galaxies we observe today. The M81 group is the perfect galaxy group to understand the past, present, and future of a group of galaxies in the process of merging. Here we measure the end of star formation (t$_{90}$) and metallicity ([M/H]) of the stellar halo of M82 and the eastern tidal stream of NGC 3077 to: 1) test the idea that M82 possesses a genuine stellar halo, formed before any interaction with M81, 2) determine if NGC 3077's tidal disruption is related to the star formation history in its tails, and 3) create a timeline of the assembly history of the central trio in the M81 group. We argue that M82 possesses a genuine, metal poor ([M/H] ~ -1.62 dex) stellar halo, formed from the merger of a small satellite galaxy roughly 6.6 Gyr ago. We also find that the stars present in NGC 3077's tails formed before tidal disruption with M81, and possesses a roughly uniform metallicity as shown in Okamoto et. al. 2023 implying that NGC 3077's progenitor had significant population gradients. Finally, we present a timeline of the central trio's merger/interaction history., Comment: 17 pages, 12 figures, 1 table, accepted for publication in ApJ

The application of large-scale models in medical image segmentation demands substantial quantities of meticulously annotated data curated by experts along with high computational resources, both of which are challenges in resource-poor settings. In this study, we present the Medical Segment Anything Model with Galore MedSAGa where we adopt the Segment Anything Model (SAM) to achieve memory-efficient, few-shot medical image segmentation by applying Gradient Low-Rank Projection GaLore to the parameters of the image encoder of SAM. Meanwhile, the weights of the prompt encoder and mask decoder undergo full parameter fine-tuning using standard optimizers. We further assess MedSAGa's few-shot learning capabilities, reporting on its memory efficiency and segmentation performance across multiple standard medical image segmentation datasets. We compare it with several baseline models, including LoRA fine-tuned SAM (SAMed) and DAE-Former. Experiments across multiple datasets and these baseline models with different number of images for fine tuning demonstrated that the GPU memory consumption of MedSAGa is significantly less than that of the baseline models, achieving an average memory efficiency of 66% more than current state-of-the-art (SOTA) models for medical image segmentation. The combination of substantially lower memory requirements and comparable to SOTA results in few-shot learning for medical image segmentation positions MedSAGa as an optimal solution for deployment in resource-constrained settings.

The study of probability distributions for random variables and their algebraic combinations has been a central focus driving the advancement of probability and statistics. Since the 1920s, the challenge of calculating the probability distributions of sums, differences, products, and quotients of independent random variables have drawn the attention of numerous statisticians and mathematicians who studied the algebraic properties and relationships of random variables. Statistical distributions are highly helpful in data science and machine learning, as they provide a range of possible values for the variables, aiding in the development of a deeper understanding of the underlying problem. In this paper, we have presented a new probability distribution based on the $\hat{I}$-function. Also, we have discussed the applications of the $\hat{I}$ function, particularly in deriving the distributions of product and the quotient involving two independent $\hat{I}$ function variates. Additionally, it has been shown that both the product and quotient of two independent $\hat{I}$-function variates also follow the $\hat{I}$-function distribution. Furthermore, the new distribution, known as the $\hat{I}$-function distribution, includes several well-known classical distributions such as the gamma, beta, exponential, normal H-function, and G-function distributions, among others, as special cases. Therefore, the $\hat{I}$-function distribution can be considered a characterization or generalization of the above-mentioned distributions., Comment: 14 pages

Integrating epitaxial BaTiO$_3$ (BTO) with Si is essential for leveraging its ferroelectric, piezoelectric, and nonlinear optical properties in microelectronics. Recently, heterogeneous integration approaches that involve growth of BTO on ideal substrates followed by transfer to a desired substrate show promise of achieving excellent device-quality films. However, beyond simple demonstrations of the existence of ferroelectricity, robust devices with high endurance were not yet demonstrated on Si using the latter approach. Here, using a novel two-step approach to synthesize epitaxial BTO using pulsed laser deposition (PLD) on water soluble Sr3Al2O7 (SAO) (on SrTiO$_3$ (STO) substrates), we demonstrate successful integration of high-quality BTO capacitors on Si, with Pr of 7 uC/cm2, Ec 150 kV/cm, ferroelectric and electromechanical endurance of greater than $10^6$ cycles. We further address the challenge of cracking and disintegration of thicker films by first transferring a large area (5 mm x 5 mm) of the templated layer of BTO (~30 nm thick) on the desired substrate, followed by the growth of high-quality BTO on this substrate, as revealed by HRXRD and HRSTEM measurements. These templated Si substrates offer a versatile platform for integrating any epitaxial complex oxides with diverse functionalities onto any inorganic substrate., Comment: 29 pages, 12 figures

This study aims to determine the awareness and adoption of Artificial Intelligence (AI) technologies in the respondent libraries of Karnataka based on demographic variables such as gender, age, academic status, and professional experience. This study employed a survey research method to evaluate the awareness and adoption of AI technologies among the respondent library professionals in Karnataka. The study employed a stratified random sampling method to select a sample of 120 respondents from a diverse population, encompassing library professionals across multiple institution types including engineering colleges, medical colleges, and degree colleges. The Chi-square test was used to analyze the data. The study revealed that there is a statistically significant difference in the awareness and adoption of AI technologies based on the factor of gender. Whereas there no significant relationship exists between the degree of awareness and adoption of AI technologies based on factors such as age, academic ranking, and professional experience. AI-powered plagiarism detection, grammar checking, and ChatGPT are the most popularly employed AI technologies among the respondents. The respondents are of the perception that AI will support Librarians and not replace them.

Our study explores how well the state-of-the-art Large Language Models (LLMs), like GPT-4 and Mistral, can assess the quality of scientific summaries or, more fittingly, scientific syntheses, comparing their evaluations to those of human annotators. We used a dataset of 100 research questions and their syntheses made by GPT-4 from abstracts of five related papers, checked against human quality ratings. The study evaluates both the closed-source GPT-4 and the open-source Mistral model's ability to rate these summaries and provide reasons for their judgments. Preliminary results show that LLMs can offer logical explanations that somewhat match the quality ratings, yet a deeper statistical analysis shows a weak correlation between LLM and human ratings, suggesting the potential and current limitations of LLMs in scientific synthesis evaluation., Comment: 4 pages, forthcoming as part of the KONVENS 2024 proceedings https://konvens-2024.univie.ac.at/

Planetary exploration requires traversal in environments with rugged terrains. In addition, Mars rovers and other planetary exploration robots often carry sensitive scientific experiments and components onboard, which must be protected from mechanical harm. This paper deals with an active suspension system focused on chassis stabilisation and an efficient traversal method while encountering unavoidable obstacles. Soft Actor-Critic (SAC) was applied along with Proportional Integral Derivative (PID) control to stabilise the chassis and traverse large obstacles at low speeds. The model uses the rover's distance from surrounding obstacles, the height of the obstacle, and the chassis' orientation to actuate the control links of the suspension accurately. Simulations carried out in the Gazebo environment are used to validate the proposed active system., Comment: 15 pages, 11 figures

Stellar halos of galaxies, primarily formed through the accretion of smaller objects, are important to understand the hierarchical mass assembly of galaxies. However, the inner regions of stellar halos in disk galaxies are predicted to have an in-situ component that is expected to be prominent along the major axis. Kinematic information is crucial to disentangle the contribution of the in-situ component from the accreted stellar halos. The low surface brightness of stellar halos makes it inaccessible with traditional integrated light spectroscopy. In this work, using a novel technique, we study the kinematics of the stellar halo of the edge-on galaxy NGC 4945. We couple new deep Multi Unit Spectroscopic Explorer spectroscopic observations with existing Hubble Space Telescope imaging data to spectroscopically measure the line-of-sight (LOS) heliocentric velocity and velocity dispersion in two fields at a galactocentric distance of 12.2 kpc (outer disk field) and 34.6 kpc (stellar halo field) along NGC 4945 major axis, by stacking individual spectra of red giant branch and asymptotic giant branch stars. We obtain a LOS velocity and dispersion of 673+/-11 km/s and 73+/-14 km/s, respectively, for the outer disk field. This is consistent with the mean HI velocity of the disk at that distance. For the halo field we obtain a LOS velocity and dispersion of 519+/-12 km/s and 42+/-22 km/s. The halo fields' velocity measurement is within ~40 km/s from the systemic LOS velocity of NGC 4945, which is 563 km/s, suggesting that its stellar halo at 34.6 kpc along the major axis is counter-rotating and is of likely accretion origin. This provides the first ever kinematic measurement of the stellar halo of a Milky Way-mass galaxy outside the Local Group from its resolved stellar population, and establishes a powerful technique for measuring the velocity field of the stellar halos of nearby galaxies., Comment: Accepted to A&A. 23 pages, 12 figures, 2 appendices

The ESO public survey VISTA Variables in the V\'ia L\'actea (VVV) surveyed the inner Galactic bulge and the adjacent southern Galactic disk from $2009-2015$. Upon its conclusion, the complementary VVV eXtended (VVVX) survey has expanded both the temporal as well as spatial coverage of the original VVV area, widening it from $562$ to $1700$ sq. deg., as well as providing additional epochs in $JHK_{\rm s}$ filters from $2016-2023$. With the completion of VVVX observations during the first semester of 2023, we present here the observing strategy, a description of data quality and access, and the legacy of VVVX. VVVX took $\sim 2000$ hours, covering about 4% of the sky in the bulge and southern disk. VVVX covered most of the gaps left between the VVV and the VISTA Hemisphere Survey (VHS) areas and extended the VVV time baseline in the obscured regions affected by high extinction and hence hidden from optical observations. VVVX provides a deep $JHK_{\rm s}$ catalogue of $\gtrsim 1.5\times10^9$ point sources, as well as a $K_{\rm s}$ band catalogue of $\sim 10^7$ variable sources. Within the existing VVV area, we produced a $5D$ map of the surveyed region by combining positions, distances, and proper motions of well-understood distance indicators such as red clump stars, RR Lyrae, and Cepheid variables. In March 2023 we successfully finished the VVVX survey observations that started in 2016, an accomplishment for ESO Paranal Observatory upon 4200 hours of observations for VVV+VVVX. The VVV+VVVX catalogues complement those from the Gaia mission at low Galactic latitudes and provide spectroscopic targets for the forthcoming ESO high-multiplex spectrographs MOONS and 4MOST., Comment: 17 pages, 11 figures (+ appendix). Accepted for publication in Astronomy and Astrophysics in section 14: Catalogs and data

This paper introduces a scholarly Question Answering (QA) system on top of the NFDI4DataScience Gateway, employing a Retrieval Augmented Generation-based (RAG) approach. The NFDI4DS Gateway, as a foundational framework, offers a unified and intuitive interface for querying various scientific databases using federated search. The RAG-based scholarly QA, powered by a Large Language Model (LLM), facilitates dynamic interaction with search results, enhancing filtering capabilities and fostering a conversational engagement with the Gateway search. The effectiveness of both the Gateway and the scholarly QA system is demonstrated through experimental analysis., Comment: 13 pages main content, 16 pages overall, 3 Figures, accepted for publication at NSLP 2024 workshop at ESWC 2024

This paper explores the impact of context selection on the efficiency of Large Language Models (LLMs) in generating Artificial Intelligence (AI) research leaderboards, a task defined as the extraction of (Task, Dataset, Metric, Score) quadruples from scholarly articles. By framing this challenge as a text generation objective and employing instruction finetuning with the FLAN-T5 collection, we introduce a novel method that surpasses traditional Natural Language Inference (NLI) approaches in adapting to new developments without a predefined taxonomy. Through experimentation with three distinct context types of varying selectivity and length, our study demonstrates the importance of effective context selection in enhancing LLM accuracy and reducing hallucinations, providing a new pathway for the reliable and efficient generation of AI leaderboards. This contribution not only advances the state of the art in leaderboard generation but also sheds light on strategies to mitigate common challenges in LLM-based information extraction., Comment: arXiv admin note: substantial text overlap with arXiv:2406.04383

The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (Task, Dataset, Metric, Score) quadruples from research papers. The findings reveal significant insights into the strengths and limitations of each model and context type, providing valuable guidance for future AI research automation efforts.

This demo will present the Research Assistant (RA) tool developed to assist with six main types of research tasks defined as standardized instruction templates, instantiated with user input, applied finally as prompts to well-known--for their sophisticated natural language processing abilities--AI tools, such as ChatGPT (https://chat.openai.com/) and Gemini (https://gemini.google.com/app). The six research tasks addressed by RA are: creating FAIR research comparisons, ideating research topics, drafting grant applications, writing scientific blogs, aiding preliminary peer reviews, and formulating enhanced literature search queries. RA's reliance on generative AI tools like ChatGPT or Gemini means the same research task assistance can be offered in any scientific discipline. We demonstrate its versatility by sharing RA outputs in Computer Science, Virology, and Climate Science, where the output with the RA tool assistance mirrored that from a domain expert who performed the same research task., Comment: 6 pages, 2 figures, accepted to the Demo track of NLDB 2024 (https://nldb2024.di.unito.it/)

In this study, we address one of the challenges of developing NER models for scholarly domains, namely the scarcity of suitable labeled data. We experiment with an approach using predictions from a fine-tuned LLM model to aid non-domain experts in annotating scientific entities within astronomy literature, with the goal of uncovering whether such a collaborative process can approximate domain expertise. Our results reveal moderate agreement between a domain expert and the LLM-assisted non-experts, as well as fair agreement between the domain expert and the LLM model's predictions. In an additional experiment, we compare the performance of finetuned and default LLMs on this task. We have also introduced a specialized scientific entity annotation scheme for astronomy, validated by a domain expert. Our approach adopts a scholarly research contribution-centric perspective, focusing exclusively on scientific entities relevant to the research theme. The resultant dataset, containing 5,000 annotated astronomy article titles, is made publicly available., Comment: 9 pages

Structured science summaries or research contributions using properties or dimensions beyond traditional keywords enhances science findability. Current methods, such as those used by the Open Research Knowledge Graph (ORKG), involve manually curating properties to describe research papers' contributions in a structured manner, but this is labor-intensive and inconsistent between the domain expert human curators. We propose using Large Language Models (LLMs) to automatically suggest these properties. However, it's essential to assess the readiness of LLMs like GPT-3.5, Llama 2, and Mistral for this task before application. Our study performs a comprehensive comparative analysis between ORKG's manually curated properties and those generated by the aforementioned state-of-the-art LLMs. We evaluate LLM performance through four unique perspectives: semantic alignment and deviation with ORKG properties, fine-grained properties mapping accuracy, SciNCL embeddings-based cosine similarity, and expert surveys comparing manual annotations with LLM outputs. These evaluations occur within a multidisciplinary science setting. Overall, LLMs show potential as recommendation systems for structuring science, but further finetuning is recommended to improve their alignment with scientific tasks and mimicry of human expertise., Comment: 22 pages, 11 figures. In review at https://www.mdpi.com/journal/information/special_issues/WYS02U2GTD

Ontology Matching (OM), is a critical task in knowledge integration, where aligning heterogeneous ontologies facilitates data interoperability and knowledge sharing. Traditional OM systems often rely on expert knowledge or predictive models, with limited exploration of the potential of Large Language Models (LLMs). We present the LLMs4OM framework, a novel approach to evaluate the effectiveness of LLMs in OM tasks. This framework utilizes two modules for retrieval and matching, respectively, enhanced by zero-shot prompting across three ontology representations: concept, concept-parent, and concept-children. Through comprehensive evaluations using 20 OM datasets from various domains, we demonstrate that LLMs, under the LLMs4OM framework, can match and even surpass the performance of traditional OM systems, particularly in complex matching scenarios. Our results highlight the potential of LLMs to significantly contribute to the field of OM., Comment: 8 pages, 1 figure, accepted to ESWC 2024 Special Track on LLMs for Knowledge Engineering (https://2024.eswc-conferences.org/call-for-papers-llms/)

Search engines these days can serve datasets as search results. Datasets get picked up by search technologies based on structured descriptions on their official web pages, informed by metadata ontologies such as the Dataset content type of schema.org. Despite this promotion of the content type dataset as a first-class citizen of search results, a vast proportion of datasets, particularly research datasets, still need to be made discoverable and, therefore, largely remain unused. This is due to the sheer volume of datasets released every day and the inability of metadata to reflect a dataset's content and context accurately. This work seeks to improve this situation for a specific class of datasets, namely research datasets, which are the result of research endeavors and are accompanied by a scholarly publication. We propose the ORKG-Dataset content type, a specialized branch of the Open Research Knowledge Graoh (ORKG) platform, which provides descriptive information and a semantic model for research datasets, integrating them with their accompanying scholarly publications. This work aims to establish a standardized framework for recording and reporting research datasets within the ORKG-Dataset content type. This, in turn, increases research dataset transparency on the web for their improved discoverability and applied use. In this paper, we present a proposal -- the minimum FAIR, comparable, semantic description of research datasets in terms of salient properties of their supporting publication. We design a specific application of the ORKG-Dataset semantic model based on 40 diverse research datasets on scientific information extraction., Comment: 8 pages, 1 figure, published in the Joint Proceedings of the Onto4FAIR 2023 Workshops

We study the fraction of the intra-cluster light (ICL) formed in-situ in the three most massive clusters of the TNG50 simulation, with virial masses $\sim 10^{14}$ M$_{\odot}$. We find that a significant fraction of ICL stars ($8\%$-$28\%$) are born in-situ. This amounts to a total stellar mass comparable to the central galaxy itself. Contrary to simple expectations, only a sub-dominant fraction of these in-situ ICL stars are born in the central regions and later re-distributed to more energetic orbits during mergers. Instead, many in-situ ICL stars form directly hundreds of kiloparsecs away from the central galaxy, in clouds condensing out of the circum-cluster medium. The simulations predict a present-date diffuse star formation rate of $\sim$1 $\mathrm{M}_{\odot}$/yr, with higher rates at higher redshifts. The diffuse star forming component of the ICL is filamentary in nature, extends for hundreds of kiloparsecs and traces the distribution of neutral gas in the cluster host halo. We discuss briefly how numerical details of the baryonic treatment in the simulation may play a role in this result and conclude that a sensitivity of $1.6 \times 10^{-19} - 2.6 \times 10^{-18}$ erg s$^{-1}$ cm$^{-2}$ arcsec$^{-2}$ in H$_\alpha$ flux (beyond current observational capabilities) would be necessary to detect this diffuse star-forming component in galaxy clusters., Comment: 10 pages, 8 figures - comments are welcome

Polysomnography (PSG) is a type of sleep study that records multimodal physiological signals and is widely used for purposes such as sleep staging and respiratory event detection. Conventional machine learning methods assume that each sleep study is associated with a fixed set of observed modalities and that all modalities are available for each sample. However, noisy and missing modalities are a common issue in real-world clinical settings. In this study, we propose a comprehensive pipeline aiming to compensate for the missing or noisy modalities when performing sleep apnea detection. Unlike other existing studies, our proposed model works with any combination of available modalities. Our experiments show that the proposed model outperforms other state-of-the-art approaches in sleep apnea detection using various subsets of available data and different levels of noise, and maintains its high performance (AUROC>0.9) even in the presence of high levels of noise or missingness. This is especially relevant in settings where the level of noise and missingness is high (such as pediatric or outside-of-clinic scenarios).

This short paper highlights the growing importance of information retrieval (IR) engines in the scientific community, addressing the inefficiency of traditional keyword-based search engines due to the rising volume of publications. The proposed solution involves structured records, underpinning advanced information technology (IT) tools, including visualization dashboards, to revolutionize how researchers access and filter articles, replacing the traditional text-heavy approach. This vision is exemplified through a proof of concept centered on the ``reproductive number estimate of infectious diseases'' research theme, using a fine-tuned large language model (LLM) to automate the creation of structured records to populate a backend database that now goes beyond keywords. The result is a next-generation IR method accessible at https://orkg.org/usecases/r0-estimates., Comment: 6 pages, 1 figure

Quantum sensors have notably advanced high-sensitivity magnetic field detection. Here, we report quantum sensors constructed from polarized spin-triplet electrons in photoexcited organic chromophores, specifically focusing on pentacene-doped para-terphenyl (${\approx}$0.1%). We demonstrate essential quantum sensing properties at room temperature: electronic optical polarization and state-dependent fluorescence contrast, by leveraging differential pumping and relaxation rates between triplet and ground states. We measure high optically detected magnetic resonance (ODMR) contrast ${\approx}16.8\%$ of the triplet states at room temperature, along with long coherence times under spin echo and CPMG sequences, $T_2{=}2.7\mu$s and $T_2^{DD}{=}18.4\mu$s respectively, limited only by the triplet lifetimes. The material offers several advantages for quantum sensing, including the ability to grow large ($cm$-scale) crystals at low cost, the absence of paramagnetic impurities, and the diamagnetism of electronic states used for sensing when not optically illuminated. Utilizing pentacene as a representative of a broader class of spin triplet-polarizable organic molecules, this study highlights new potential for quantum sensing in chemical systems.

Recent breakthroughs in large language models (LLMs) have centered around a handful of data-rich languages. What does it take to broaden access to breakthroughs beyond first-class citizen languages? Our work introduces Aya, a massively multilingual generative language model that follows instructions in 101 languages of which over 50% are considered as lower-resourced. Aya outperforms mT0 and BLOOMZ on the majority of tasks while covering double the number of languages. We introduce extensive new evaluation suites that broaden the state-of-art for multilingual eval across 99 languages -- including discriminative and generative tasks, human evaluation, and simulated win rates that cover both held-out tasks and in-distribution performance. Furthermore, we conduct detailed investigations on the optimal finetuning mixture composition, data pruning, as well as the toxicity, bias, and safety of our models. We open-source our instruction datasets and our model at https://hf.co/CohereForAI/aya-101