Linguistic commentary on LLMs, heavily influenced by the theoretical frameworks of de Saussure and Chomsky, is often speculative and unproductive. Critics challenge whether LLMs can legitimately model language, citing the need for "deep structure" or "grounding" to achieve an idealized linguistic "competence." We argue for a radical shift in perspective towards the empiricist principles of Witold Mańczak, a prominent general and historical linguist. He defines language not as a "system of signs" or a "computational system of the brain" but as the totality of all that is said and written. Above all, he identifies frequency of use of particular language elements as language's primary governing principle. Using his framework, we challenge prior critiques of LLMs and provide a constructive guide for designing, evaluating, and interpreting language models.

University College London Summary This study presents an innovative approach to urban mobility simulation by integrating a Large Language Model (LLM) with Agent-Based Modeling (ABM). Unlike traditional rule-based ABM, the proposed framework leverages LLM to enhance agent diversity and realism by generating synthetic population profiles, allocating routine and occasional locations, and simulating personalized routes. Key insights, such as route heat maps and mode-specific indicators, provide urban planners with actionable information for policy-making. Future work focuses on establishing robust validation frameworks to ensure accuracy and reliability in urban planning applications. KEYWORDS: Mobility simulation, Agent-Based Modeling (ABM), Large Language Model (LLM), Synthetic profiles, Urban planning 1. Introduction Mobility reflects the unique geographic, economic, and cultural contexts of cities while being shaped by and confined to the urban infrastructure that supports it.

Recently, Large Language Models (LLMs) with Mixture of Experts (MoE) layers have gained significant attention. Currently, state-of-the-art LLMs utilize this architecture. There is a substantial amount of research on how to train such models and how to select hyperparameters for this architecture. However, there is a lack of studies focusing on post-evaluation analysis of MoE layer properties. In this paper, we take a first step toward closing this gap by evaluating expert contributions on the quiz-based MMLU benchmark. We show that most experts were never activated during inference on this benchmark. Additionally, the output distribution of gating networks is much closer to uniform than sparse. Finally, we demonstrate that the average performance of some experts within the same layer varies significantly.

This study investigates gender bias in large language models (LLMs) by comparing their gender perception to that of human respondents, U.S. Bureau of Labor Statistics data, and a 50% no-bias benchmark. We created a new evaluation set using occupational data and role-specific sentences. Unlike common benchmarks included in LLM training data, our set is newly developed, preventing data leakage and test set contamination. Five LLMs were tested to predict the gender for each role using single-word answers. We used Kullback-Leibler (KL) divergence to compare model outputs with human perceptions, statistical data, and the 50% neutrality benchmark. All LLMs showed significant deviation from gender neutrality and aligned more with statistical data, still reflecting inherent biases.

Although the automatic identification of the optimal fingering for the performance of melodies on fretted string instruments has already been addressed (at least partially) in the literature, the specific case regarding lead electric guitar requires a dedicated approach. We propose a system that can generate, from simple MIDI melodies, tablatures enriched by fingerings, articulations, and expressive techniques. The basic fingering is derived by solving a constrained and multi-attribute optimization problem, which derives the best position of the fretting hand, not just the finger used at each moment.Then, by analyzing statistical data from the mySongBook corpus, the most common clich{\'e}s and biomechanical feasibility, articulations, and expressive techniques are introduced. Finally, the obtained output is converted into MusicXML format, which allows for easy visualization and use. The quality of the tablatures derived and the high configurability of the proposed approach can have several impacts, in particular in the fields of instrumental teaching, assisted composition and arranging, and computational expressive music performance models.

Emotion prediction is the field of study to understand human emotions. Existing methods focus on modalities like text, audio, facial expressions, etc., which could be private to the user. Emotion can be derived from the subject's psychological data as well. Various approaches that employ combinations of physiological sensors for emotion recognition have been proposed. Yet, not all sensors are simple to use and handy for individuals in their daily lives. Thus, we propose a system to predict user emotion using smartwatch sensors. We design a framework to collect ground truth in real-time utilizing a mix of English and regional language-based videos to invoke emotions in participants and collect the data. Further, we modeled the problem as binary classification due to the limited dataset size and experimented with multiple machine-learning models. We also did an ablation study to understand the impact of features including Heart Rate, Accelerometer, and Gyroscope sensor data on mood. From the experimental results, Multi-Layer Perceptron has shown a maximum accuracy of 93.75 percent for pleasant-unpleasant (high/low valence classification) moods.

Flooding is one of the most destructive and costly natural disasters, and climate changes would further increase risks globally. This work presents a novel multimodal machine learning approach for multi-year global flood risk prediction, combining geographical information and historical natural disaster dataset. Our multimodal framework employs state-of-the-art processing techniques to extract embeddings from each data modality, including text-based geographical data and tabular-based time-series data. Experiments demonstrate that a multimodal approach, that is combining text and statistical data, outperforms a single-modality approach. Our most advanced architecture, employing embeddings extracted using transfer learning upon DistilBert model, achieves 75\%-77\% ROCAUC score in predicting the next 1-5 year flooding event in historically flooded locations. This work demonstrates the potentials of using machine learning for long-term planning in natural disaster management.

We present a new lossy compression algorithm for statistical floating-point data through a representation learning with binary variables. The algorithm finds a set of basis vectors and their binary coefficients that precisely reconstruct the original data. The optimization for the basis vectors is performed classically, while binary coefficients are retrieved through both simulated and quantum annealing for comparison. A bias correction procedure is also presented to estimate and eliminate the error and bias introduced from the inexact reconstruction of the lossy compression for statistical data analyses. The compression algorithm is demonstrated on two different datasets of lattice quantum chromodynamics simulations. The results obtained using simulated annealing show 3.5 times better compression performance than the algorithms based on a neural-network autoencoder and principal component analysis. Calculations using quantum annealing also show promising results, but performance is limited by the integrated control error of the quantum processing unit, which yields large uncertainties in the biases and coupling parameters. Hardware comparison is further studied between the previous generation D-Wave 2000Q and the current D-Wave Advantage system. Our study shows that the Advantage system is more likely to obtain low-energy solutions for the problems than the 2000Q.

This paper describes a machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple distinct ML techniques and utilizing diverse data sources. Our framework, which we refer to as Hurricast (HURR), is built upon the combination of distinct data processing techniques using gradient-boosted trees and novel encoder-decoder architectures, including CNN, GRU and Transformers components. We propose a deep-feature extractor methodology to mix spatial-temporal data with statistical data efficiently. Our multimodal framework unleashes the potential of making forecasts based on a wide range of data sources, including historical storm data, reanalysis atmospheric images, and operational forecasts. Evaluating our models with current operational forecasts in North Atlantic and Eastern Pacific basins on the last years of available data, results show our models consistently outperform statistical-dynamical models and, albeit less accurate than the best dynamical models, our framework computes forecasts in seconds. Furthermore, the inclusion of Hurricast into an operational forecast consensus model leads to a significant improvement of 5% - 15% over NHC's official forecast, thus highlighting the complementary properties with existing approaches. In summary, our work demonstrates that combining different data sources and distinct machine learning methodologies can lead to superior tropical cyclone forecasting.

We argue that while this discourse on data ethics is of critical importance, it is missing one fundamental point: If more and more efforts in business, government, science, and our daily lives are data-driven, we should pay more attention to what exactly we are driven by. Therefore, we need more debate on what fundamental properties constitute data. In the first section of the paper, we work from the fundamental properties necessary for statistical computation to a definition of statistical data. We define a statistical datum as the coming together of substantive and numerical properties and differentiate between qualitative and quantitative data. Subsequently, we qualify our definition by arguing that for data to be practically useful, it needs to be commensurable in a manner that reveals meaningful differences that allow for the generation of relevant insights through statistical methodologies. In the second section, we focus on what our conception of data can contribute to the discourse on data ethics and beyond. First, we hold that the need for useful data to be commensurable rules out an understanding of properties as fundamentally unique or equal. Second, we argue that practical concerns lead us to increasingly standardize how we operationalize a substantive property; in other words, how we formalize the relationship between the substantive and numerical properties of data. Thereby, we also standardize the interpretation of a property. With our increasing reliance on data and data technologies, these two characteristics of data affect our collective conception of reality. Statistical data's exclusion of the fundamentally unique and equal influences our perspective on the world, and the standardization of substantive properties can be viewed as profound ontological practice, entrenching ever more pervasive interpretations of phenomena in our everyday lives.