Search

Context: Generative AI (GenAI) has emerged as a transformative tool in software engineering, with requirements engineering (RE) actively exploring its potential to revolutionize processes and outcomes. The integration of GenAI into RE presents both promising opportunities and significant challenges that necessitate systematic analysis and evaluation. Objective: This paper presents a comprehensive systematic literature review (SLR) analyzing state-of-the-art applications and innovative proposals leveraging GenAI in RE. It surveys studies focusing on the utilization of GenAI to enhance RE processes while identifying key challenges and opportunities in this rapidly evolving field. Method: A rigorous SLR methodology was used to analyze 27 carefully selected primary studies in-depth. The review examined research questions pertaining to the application of GenAI across various RE phases, the models and techniques used, and the challenges encountered in implementation and adoption. Results: The most salient findings include i) a predominant focus on the early stages of RE, particularly the elicitation and analysis of requirements, indicating potential for expansion into later phases; ii) the dominance of large language models, especially the GPT series, highlighting the need for diverse AI approaches; and iii) persistent challenges in domain-specific applications and the interpretability of AI-generated outputs, underscoring areas requiring further research and development. Conclusions: The results highlight the critical need for comprehensive evaluation frameworks, improved human-AI collaboration models, and thorough consideration of ethical implications in GenAI-assisted RE. Future research should prioritize extending GenAI applications across the entire RE lifecycle, enhancing domain-specific capabilities, and developing strategies for responsible AI integration in RE practices.

We consider a semi-supervised classification problem with non-stationary label-shift in which we observe a labelled data set followed by a sequence of unlabelled covariate vectors in which the marginal probabilities of the class labels may change over time. Our objective is to predict the corresponding class-label for each covariate vector, without ever observing the ground-truth labels, beyond the initial labelled data set. Previous work has demonstrated the potential of sophisticated variants of online gradient descent to perform competitively with the optimal dynamic strategy (Bai et al. 2022). In this work we explore an alternative approach grounded in statistical methods for adaptive transfer learning. We demonstrate the merits of this alternative methodology by establishing a high-probability regret bound on the test error at any given individual test-time, which adapt automatically to the unknown dynamics of the marginal label probabilities. Further more, we give bounds on the average dynamic regret which match the average guarantees of the online learning perspective for any given time interval.

Extreme temperature outages can lead to not just economic losses but also various non-energy impacts (NEI) due to significant degradation of indoor operating conditions caused by service disruptions. However, existing resilience assessment approaches lack specificity for extreme temperature conditions. They often overlook temperature-related mortality and neglect the customer characteristics and grid response in the calculation, despite the significant influence of these factors on NEI-related economic losses. This paper aims to address these gaps by introducing a comprehensive framework to estimate the impact of resilience enhancement not only on the direct economic losses incurred by customers but also on potential NEI, including mortality and the value of statistical life during extreme temperature-related outages. The proposed resilience valuation integrates customer characteristics and grid response variables based on a scalable grid simulation environment. This study adopts a holistic approach to quantify customer-oriented economic impacts, utilizing probabilistic loss scenarios that incorporate health-related factors and damage/loss models as a function of exposure for valuation. The proposed methodology is demonstrated through comparative resilient outage planning, using grid response models emulating a Texas weather zone during the 2021 winter storm Uri. The case study results show that enhanced outage planning with hardened infrastructure can improve the system resilience and thereby reduce the relative risk of mortality by 16% and save the total costs related to non-energy impacts by 74%. These findings underscore the efficacy of the framework by assessing the financial implications of each case, providing valuable insights for decision-makers and stakeholders involved in extreme-weather related resilience planning for risk management and mitigation strategies.

The Dvoretzky--Kiefer--Wolfowitz--Massart inequality gives a sub-Gaussian tail bound on the supremum norm distance between the empirical distribution function of a random sample and its population counterpart. We provide a short proof of a result that improves the existing bound in two respects. First, our one-sided bound holds without any restrictions on the failure probability, thereby verifying a conjecture of Birnbaum and McCarty (1958). Second, it is local in the sense that it holds uniformly over sub-intervals of the real line with an error rate that adapts to the behaviour of the population distribution function on the interval.

We present a comparative study of the effect of low-temperature opacities on stellar models up to the Red Giant branch (RGB), computed with the GARching STellar Evolution Code. We have used two sets of low-temperature opacities; {\AE}SOPUS ({\AE}) from the University of Padova and those from the Wichita State University group (F05). In the relevant range of temperatures for this study, log \k{appa}{\AE} < log \k{appa}F 05. Therefore, to compare stellar evolutionary tracks, we performed a solar calibration of the {\alpha}mlt, for each set of low-temperature opacities. After carrying such a calibration, we find that stellar evolutionary tracks are almost unaffected by the choice of low-temperature opacities, with largest variations of 25-30 K at the latest evolutionary stages of the RGB phase.

Recognizing text lines from images is a challenging problem, especially for handwritten documents due to large variations in writing styles. While text line recognition models are generally trained on large corpora of real and synthetic data, such models can still make frequent mistakes if the handwriting is inscrutable or the image acquisition process adds corruptions, such as noise, blur, compression, etc. Writing style is generally quite consistent for an individual, which can be leveraged to correct mistakes made by such models. Motivated by this, we introduce the problem of adapting text line recognition models during test time. We focus on a challenging and realistic setting where, given only a single test image consisting of multiple text lines, the task is to adapt the model such that it performs better on the image, without any labels. We propose an iterative self-training approach that uses feedback from the language model to update the optical model, with confident self-labels in each iteration. The confidence measure is based on an augmentation mechanism that evaluates the divergence of the prediction of the model in a local region. We perform rigorous evaluation of our method on several benchmark datasets as well as their corrupted versions. Experimental results on multiple datasets spanning multiple scripts show that the proposed adaptation method offers an absolute improvement of up to 8% in character error rate with just a few iterations of self-training at test time.

Language models are useful adjuncts to optical models for producing accurate optical character recognition (OCR) results. One factor which limits the power of language models in this context is the existence of many specialized domains with language statistics very different from those implied by a general language model - think of checks, medical prescriptions, and many other specialized document classes. This paper introduces an algorithm for efficiently generating and attaching a domain specific word based language model at run time to a general language model in an OCR system. In order to best use this model the paper also introduces a modified CTC beam search decoder which effectively allows hypotheses to remain in contention based on possible future completion of vocabulary words. The result is a substantial reduction in word error rate in recognizing material from specialized domains.

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) -- languages for which NLP re-search is particularly far behind in meeting user needs -- it is feasible to annotate small amounts of data. Motivated by this, we propose XTREME-UP, a benchmark defined by: its focus on the scarce-data scenario rather than zero-shot; its focus on user-centric tasks -- tasks with broad adoption by speakers of high-resource languages; and its focus on under-represented languages where this scarce-data scenario tends to be most realistic. XTREME-UP evaluates the capabilities of language models across 88 under-represented languages over 9 key user-centric technologies including ASR, OCR, MT, and information access tasks that are of general utility. We create new datasets for OCR, autocomplete, semantic parsing, and transliteration, and build on and refine existing datasets for other tasks. XTREME-UP provides methodology for evaluating many modeling scenarios including text-only, multi-modal (vision, audio, and text),supervised parameter tuning, and in-context learning. We evaluate commonly used models on the benchmark. We release all code and scripts to train and evaluate models

Given a sample of covariate-response pairs, we consider the subgroup selection problem of identifying a subset of the covariate domain where the regression function exceeds a pre-determined threshold. We introduce a computationally-feasible approach for subgroup selection in the context of multivariate isotonic regression based on martingale tests and multiple testing procedures for logically-structured hypotheses. Our proposed procedure satisfies a non-asymptotic, uniform Type I error rate guarantee with power that attains the minimax optimal rate up to poly-logarithmic factors. Extensions cover classification, isotonic quantile regression and heterogeneous treatment effect settings. Numerical studies on both simulated and real data confirm the practical effectiveness of our proposal, which is implemented in the R package ISS., Comment: 69 pages, 20 figures

We present recent 2-port vector network analyzer (VNA) measurements of the complete set of scattering parameters for the antenna used within the Long Wavelength Array (LWA) and the associated front end electronics (FEEs). Full scattering parameter measurements of the antenna yield not only the reflection coefficient for each polarization, S11 and S22, but also the coupling between polarizations, S12 and S21. These had been previously modeled using simulations, but direct measurements had not been obtained until now. The measurements are used to derive a frequency dependent impedance mismatch factor (IMF) which represents the fraction of power that is passed through the antenna-FEE interface and not reflected due to a mismatch between the impedance of the antenna and the impedance of the FEE. We also present results from a two antenna experiment where each antenna is hooked up to a separate port on the VNA. This allows for cross-antenna coupling to be measured for all four possible polarization combinations. Finally, we apply the newly measured IMF and FEE forward gain corrections to LWA data to investigate how well they remove instrumental effects., Comment: 16 pages, 12 figures, Accepted for publication in Publications of the Astronomical Society of the Pacific

The classical van der Waals equation, applied to one or two mixing fluids, and the Helmholtz (free) energy function $A$ yield, for fixed temperature $T$, a curve in the plane $\mathbb{R}^2$ (one fluid) or a surface in 3-space $\mathbb{R}^3$ (binary fluid). A line tangent to this curve in two places (bitangent line), or a set of planes tangent to this surface in two places (bitangent planes) have a thermodynamic significance which is well documented in the classical literature. Points of contact of bitangent planes trace `binodal curves' on the surface in $\mathbb{R}^3$. The study of these bitangents is also classical, starting with D.J. Korteweg and J.D. van der Waals at the end of the $19^{\rm th}$ century, but continuing into modern times. In this paper we give a summary of the thermodynamic background and of other mathematical investigations and then present a new mathematical approach which classifies a wide range of situations in $\mathbb{R}^3$ where bitangents occur. In particular, we are able to justify many of the details in diagrams of binodal curves observed by Korteweg and others, using techniques from singularity theory., Comment: 26 pages, 9 figures

The combined effect of disorder and interactions is central to the richness of condensed matter physics and can lead to novel quantum states such as the Bose glass phase in disordered bosonic systems. Here, we report on the experimental realisation of the two-dimensional Bose glass using ultra-cold atoms in an eight-fold symmetric quasicrystalline optical lattice. By probing the coherence properties of the system, we observe a Bose glass to superfluid transition and map out the phase diagram in the weakly interacting regime. Moreover, we reveal the non-ergodic nature of the Bose glass by probing the capability to restore coherence. Our observations are in good agreement with recent quantum Monte Carlo predictions and pave the way for experimentally testing the connection between the Bose glass, many-body localisation, and glassy dynamics more generally.