Assessing the quality of group deliberation is essential for improving our understanding of deliberative processes. The Deliberative Reason Index (DRI) offers a sophisticated metric for evaluating group reasoning, but its implementation has been constrained by the complex and time-consuming process of statement generation. This thesis introduces an innovative, automated approach to DRI statement generation that leverages advanced natural language processing (NLP) and large language models (LLMs) to substantially reduce the human effort involved in survey preparation. Key contributions are a systematic framework for automated DRI statement generation and a methodological innovation that significantly lowers the barrier to conducting comprehensive deliberative process assessments. In addition, the findings provide a replicable template for integrating generative artificial intelligence into social science research methodologies.

We present ARCTraj, a dataset and methodological framework for modeling human reasoning through complex visual tasks in the Abstraction and Reasoning Corpus (ARC). While ARC has inspired extensive research on abstract reasoning, most existing approaches rely on static input--output supervision, which limits insight into how reasoning unfolds over time. ARCTraj addresses this gap by recording temporally ordered, object-level actions that capture how humans iteratively transform inputs into outputs, revealing intermediate reasoning steps that conventional datasets overlook. Collected via the O2ARC web interface, it contains around 10,000 trajectories annotated with task identifiers, timestamps, and success labels across 400 training tasks from the ARC-AGI-1 benchmark. It further defines a unified reasoning pipeline encompassing data collection, action abstraction, Markov decision process (MDP) formulation, and downstream learning, enabling integration with reinforcement learning, generative modeling, and sequence modeling methods such as PPO, World Models, GFlowNets, Diffusion agents, and Decision Transformers. Analyses of spatial selection, color attribution, and strategic convergence highlight the structure and diversity of human reasoning. Together, these contributions position ARCTraj as a structured and interpretable foundation for studying human-like reasoning, advancing explainability, alignment, and generalizable intelligence.

Linear Predictive Clustering (LPC) partitions samples based on shared linear relationships between feature and target variables, with numerous applications including marketing, medicine, and education. Greedy optimization methods, commonly used for LPC, alternate between clustering and linear regression but lack global optimality. While effective for separable clusters, they struggle in non-separable settings where clusters overlap in feature space. In an alternative constrained optimization paradigm, Bertsimas and Shioda (2007) formulated LPC as a Mixed-Integer Program (MIP), ensuring global optimality regardless of separability but suffering from poor scalability. This work builds on the constrained optimization paradigm to introduce two novel approaches that improve the efficiency of global optimization for LPC. By leveraging key theoretical properties of separability, we derive near-optimal approximations with provable error bounds, significantly reducing the MIP formulation's complexity and improving scalability. Additionally, we can further approximate LPC as a Quadratic Pseudo-Boolean Optimization (QPBO) problem, achieving substantial computational improvements in some settings. Comparative analyses on synthetic and real-world datasets demonstrate that our methods consistently achieve near-optimal solutions with substantially lower regression errors than greedy optimization while exhibiting superior scalability over existing MIP formulations.

In the context of pretraining of Large Language Models (LLMs), synthetic data has emerged as an alternative for generating high-quality pretraining data at scale. This is particularly beneficial in low-resource language settings where the benefits of recent LLMs have been unevenly distributed across languages. In this work, we present a systematic study on the generation and evaluation of synthetic multilingual pretraining data for Indic languages, where we construct a large-scale synthetic dataset BhashaKritika, comprising 540B tokens using 5 different techniques for 10 languages. We explore the impact of grounding generation in documents, personas, and topics. We analyze how language choice, both in the prompt instructions and document grounding, affects data quality, and we compare translations of English content with native generation in Indic languages. To support scalable and language-sensitive evaluation, we introduce a modular quality evaluation pipeline that integrates script and language detection, metadata consistency checks, n-gram repetition analysis, and perplexity-based filtering using KenLM models. Our framework enables robust quality control across diverse scripts and linguistic contexts. Empirical results through model runs reveal key trade-offs in generation strategies and highlight best practices for constructing effective multilingual corpora.

Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA frameworks like TrustUQA. However, these frameworks face challenges when applied to small-scale LLMs since small-scale LLMs are prone to errors in generating structured queries. To improve the structured data QA ability of small-scale LLMs, we propose a self-correction distillation (SCD) method. In SCD, an error prompt mechanism (EPM) is designed to detect errors and provide customized error messages during inference, and a two-stage distillation strategy is designed to transfer large-scale LLMs' query-generation and error-correction capabilities to small-scale LLM. Experiments across 5 benchmarks with 3 structured data types demonstrate that our SCD achieves the best performance and superior generalization on small-scale LLM (8B) compared to other distillation methods, and closely approaches the performance of GPT4 on some datasets. Furthermore, large-scale LLMs equipped with EPM surpass the state-of-the-art results on most datasets.

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies noisy, high-entropy signals and is especially harmful under large teacher-student capacity gaps. We introduce SelecTKD, a plug-and-play Selective Token-Weighted distillation framework that shifts the focus from "how to measure divergence" to "where to apply learning". At each step, the student proposes tokens that are verified by the teacher through a robust propose-and-verify procedure with two variants: greedy Top-k and non-greedy Spec-k. Accepted tokens receive full loss, while rejected tokens are masked or down-weighted. This objective-agnostic design works with on- and off-policy data, induces an implicit curriculum quantified by Token Acceptance Rate (TAR), and stabilizes optimization. Across instruction following, mathematical reasoning, code generation, and a VLM setting, SelecTKD consistently improves strong baselines and achieves state-of-the-art results for small models without architectural changes or extra reference models.

Abstract-- Learned robot policies have consistently been shown to be versatile, but they typically have no built-in mechanism for handling the complexity of open environments, making them prone to execution failures; this implies that deploying policies without the ability to recognise and react to failures may lead to unreliable and unsafe robot behaviour . In this paper, we present a framework that couples a learned policy with a method to detect visual anomalies during policy deployment and to perform recovery behaviours when necessary, thereby aiming to prevent failures. Specifically, we train an anomaly detection model using data collected during nominal executions of a trained policy. This model is then integrated into the online policy execution process, so that deviations from the nominal execution can trigger a three-level sequential recovery process that consists of (i) pausing the execution temporarily, (ii) performing a local perturbation of the robot's state, and (iii) resetting the robot to a safe state by sampling from a learned execution success model. We verify our proposed method in two different scenarios: (i) a door handle reaching task with a Kinova Gen3 arm using a policy trained in simulation and transferred to the real robot, and (ii) an object placing task with a UFactory xArm 6 using a general-purpose policy model. Our results show that integrating policy execution with anomaly detection and recovery increases the execution success rate in environments with various anomalies, such as trajectory deviations and adversarial human interventions. I. INTRODUCTION To increase the flexibility of a robot's execution and reduce the requirements on explicitly modelling the execution process, robot execution policies are often acquired using learning methods, such as imitation learning or reinforcement learning (RL).

Identifying the determinants of academic success in basic education represents a central challenge for educational research and policymaking, particularly in a country with Brazil's vast dimensions and socioeconomic heterogeneity (Issah et al. 2023). A systemic approach is crucial, as student performance is influenced by a complex interplay of factors spanning individual, academic, socioeconomic, and institutional domains (Barrag an Moreno and Guzm an Rinc on 2025). The System of Assessment of Basic Education (SAEB), conducted by the National Institute for Educational Studies and Research An ısio Teixeira (INEP) (INEP 2025), provides a rich, multi-level dataset uniquely suited for such an analysis (Bonamino et al. 2010). The public availability of its anonymized microdata enables the research community to investigate the intricate relationships between student proficiency and a wide array of contextual factors, from socioeconomic backgrounds to school infrastructure and teacher profiles. Consequently, the SAEB microdata is an essential resource for data-driven research aimed at informing and evaluating educational policies in the country (Lundberg and Lee 2017b; Mazoni and Oliveira 2023). While traditional statistical methods are common, the Educational Data Mining (EDM) paradigm offers powerful tools for uncovering complex, non-linear patterns from such data (Romero and Ventura 2010). Furthermore, we demonstrate that by interpreting the model's classification results with XAI techniques, our method provides data-driven insights for educators and policymakers (Idrizi 2024). The primary objective of this research is thus to develop and evaluate a multi-level machine learning model to identify the key systemic factors associated with the academic performance of 9th-grade and high school students, using the SAEB microdata. Building upon this perspective, the study shifts its analytical focus from purely individual student interventions toward addressing the systemic determinants that shape educational outcomes in Brazilian basic education.

We explore the use of expert-guided bandit learning, which we refer to as online mixture-of-experts (OMoE). In this setting, given a context, a candidate committee of experts must determine how to aggregate their outputs to achieve optimal results in terms of aggregate accuracy. We propose two algorithms to address this problem. The first algorithm combines aggregate voting with UCB-driven successive elimination, efficiently pruning suboptimal exploration actions. The second algorithm employs an online weighted-majority-voting mechanism, leveraging the respective voting power of each expert proportional to their predictive power. We derive theoretical guarantees for the regret properties in the bandit setting under ideal circumstances, and empirical results are provided accordingly. As a modern study on applications, these methods are applied to the online fine-tuning of a set of expert large language models (LLMs), where after each response, the generative LLM dynamically reweighs its set of experts and/or selects the optimal committee of experts to generate the most accurate response. Our results introduce new methodologies and no-regret guarantees for combining multiple experts to improve on the performance of the an aggregate model overall.

Dedicated analog neurocomputing circuits are promising for high-throughput, low power consumption applications of machine learning (ML) and for applications where implementing a digital computer is unwieldy (remote locations; small, mobile, and autonomous devices, extreme conditions, etc.). Neural networks (NN) implemented in such circuits, however, must contend with circuit noise and the non-uniform shapes of the neuron activation function (NAF) due to the dispersion of performance characteristics of circuit elements (such as transistors or diodes implementing the neurons). We present a computational study of the impact of circuit noise and NAF inhomogeneity in function of NN architecture and training regimes. We focus on one application that requires high-throughput ML: materials informatics, using as representative problem ML of formation energies vs. lowest-energy isomer of peri-condensed hydrocarbons, formation energies and band gaps of double perovskites, and zero point vibrational energies of molecules from QM9 dataset. We show that NNs generally possess low noise tolerance with the model accuracy rapidly degrading with noise level. Single-hidden layer NNs, and NNs with larger-than-optimal sizes are somewhat more noise-tolerant. Models that show less overfitting (not necessarily the lowest test set error) are more noise-tolerant. Importantly, we demonstrate that the effect of activation function inhomogeneity can be palliated by retraining the NN using practically realized shapes of NAFs.