In Natural Language Processing (NLP), one of the most important tasks is text-to-SQL semantic parsing, which focuses on enabling users to interact with the database in a more natural manner. In recent years, text-to-SQL has made significant progress, but most were English-centric. In this paper, we introduce Ar-Spider ¹, the first Arabic cross-domain text-to-SQL dataset. Due to the unique nature of the language, two major challenges have been encountered, namely schema linguistic and SQL structural challenges. In order to handle these issues and conduct the experiments, we adopt two baseline models LGESQL [4] and S²SQL [12], both of which are tested with two cross-lingual models to alleviate the effects of schema linguistic and SQL structure linking challenges. The baselines demonstrate decent single-language performance on our Arabic text-to-SQL dataset, Ar-Spider, achieving 62.48% for S²SQL and 65.57% for LGESQL, only 8.79% below the highest results achieved by the baselines when trained in English dataset. To achieve better performance on Arabic text-to-SQL, we propose the context similarity relationship (CSR) approach, which results in a significant increase in the overall performance of about 1.52% for S²SQL and 1.06% for LGESQL and closes the gap between Arabic and English languages to 7.73%.

In the semantic parsing domain, significant progress has been achieved in Text-to-SQL and question-answering tasks, both focused on extracting information from data sources in their native format. However, the inherent constraints of their formal meaning representations, such as SQL programming language, hinder their ability to analyze data from various perspectives, such as conducting statistical analyses. To address this limitation and inspire research in this field, we design SIGMA, a new dataset for Text-to-Code semantic parsing with statistical analysis. SIGMA consists of 6000 questions with corresponding Python code labels. The Python code labels in our dataset cover 4 types of query patterns, which return data in their original format, and 40 types of statistical analysis patterns, which perform statistical operations on the data. We evaluated the SIGMA dataset using three different baseline models: LGESQL, 5mBoP, and SLSQL. The experimental results show that the LGESQL model with ELECTRA outperforms all other models, achieving 83.37% structure accuracy. In terms of execution accuracy, the 5mBoP model, when combined with GraPPa and T5, reaches 76.38%.

Hallucination has become a serious concern in large language models (LLMs), as these models can generate useful yet incorrect or misleading information, which has led to growing research interest in retrieval-augmented generation (RAG) as a mitigation approach. RAG provides LLMs with access to external information, such as databases or documents, which can help them to answer users' questions. Currently, several benchmarks released measure RAG performance on various LLMs; however, evaluations of the noise robustness ability in Arabic are absent. In this paper, we systematically investigated the capabilities of state-of-the-art multilingual LLMs with regard to two essential RAG abilities, noise robustness and negative rejection. To accomplish this, we generated an Arabic benchmark consisting of 300 questions along with 6,196 documents. Then, we assessed the performance of six LLMs in relation to the two aforementioned RAG abilities. The results reveal that all six LLMs were negatively affected when the noise ratio in the external documents was increased. Under the highest noise settings at 80%, the best LLM performance was for Claude-4 sonnet, in which their performance decreased by only 4.67 percentage points. Furthermore, when it comes to the negative rejection task, there has been a significant impact on all six models. The best two models, Claude-4 sonnet and Llama-4, scored 90.67% and 85.67%, respectively, while smaller models, like GPT-3.5, scored 69.33%. Furthermore, our manual analysis reveals that many errors made by LLMs are attributed to over-caution behavior. LLMs often decline to respond probably due to training mechanisms designed to reduce hallucinations. Additionally, other errors occur when there is a high lexical similarity between the question and the words of noisy documents, which causes the model to rely on irrelevant content instead of the correct information.

Background/Objective: Autonomous vehicles (AVs) require control algorithms capable of handling complex and dynamic environments while satisfying multiple conflicting objectives such as safety, comfort, energy efficiency, and trajectory accuracy. Model predictive control (MPC) offers a principled framework for multi-constraint optimization, yet its real-time feasibility remains challenging for nonlinear vehicle dynamics. Methods: This paper presents a feedforward neural network (FNN)-based MPC framework for autonomous vehicle trajectory tracking. The FNN approximates the coupled vehicle dynamics and visual preview error model using an algebraic sum of log-sigmoid functions. Three adaptive FNN parameter sets, namely, the scaling factor, convergence parameter, and time-shifting parameter, are jointly optimized using a hybrid algorithm that combines the global search capability of fractional particle swarm optimization (FPSO) with the local refinement of sequential quadratic programming (SQP). Results: Comprehensive scenario-based simulations are performed to evaluate trajectory tracking dynamics under dry conditions with an adhesion coefficient of 0.8 and a vehicle mass of 1723 kg moving at a speed of 80 km/h. The results are quantitatively compared with a traditional PID controller and a structurally comparable MPC framework from the literature under identical simulation conditions; related DRL- and RL-based methods are discussed qualitatively for contextual orientation only. The stability, reliability, and computational complexity of the proposed framework are examined based on the mean square error, fitness value, and computational budget in GFLOPs for 100 independent runs. Conclusions: The proposed FNN-based MPC framework demonstrates improved tracking accuracy and optimizer reliability in simulation. While the present results indicate promising computational behavior, real-time deployment will require further validation on embedded automotive hardware and under closed-loop real-time constraints.