Spider, the SOT A, in terms of execution accuracy, was 79.9 and the new SOT A at

Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control policies by answering when authorized and refusing when not. To evaluate this behavior, we created a novel dataset that extends the Spider and BIRD text-to-SQL datasets, both of which have been modified with realistic PostgreSQL role-based policies at the table and column levels. We compare three designs: (i) zero or few-shot prompting, (ii) a two-step generator-verifier pipeline that checks SQL against policy, and (iii) LoRA fine-tuned models that learn permission awareness directly. Across multiple model families, explicit verification (the two-step framework) improves refusal precision and lowers false permits. At the same time, fine-tuning achieves a stronger balance between safety and utility (i.e., when considering execution accuracy). Longer and more complex policies consistently reduce the reliability of all systems. We release RBAC-augmented datasets and code.

Spider, the SOT A, in terms of execution accuracy, was 79.9 and the new SOT A at

Neural Architecture Search (NAS) has garnered significant research interest due to its capability to discover architectures superior to manually designed ones. Learning text representation is crucial for text classification and other language-related tasks. The NAS model used in text classification does not have a Hybrid hierarchical structure, and there is no restriction on the architecture structure, due to which the search space becomes very large and mostly redundant, so the existing RL models are not able to navigate the search space effectively. Also, doing a flat architecture search leads to an unorganised search space, which is difficult to traverse. For this purpose, we propose HHNAS-AM (Hierarchical Hybrid Neural Architecture Search with Adaptive Mutation Policies), a novel approach that efficiently explores diverse architectural configurations. We introduce a few architectural templates to search on which organise the search spaces, where search spaces are designed on the basis of domain-specific cues. Our method employs mutation strategies that dynamically adapt based on performance feedback from previous iterations using Q-learning, enabling a more effective and accelerated traversal of the search space. The proposed model is fully probabilistic, enabling effective exploration of the search space. We evaluate our approach on the database id (db_id) prediction task, where it consistently discovers high-performing architectures across multiple experiments. On the Spider dataset, our method achieves an 8% improvement in test accuracy over existing baselines.

Confidence estimation for text-to-SQL aims to assess the reliability of model-generated SQL queries without having access to gold answers. We study this problem in the context of large language models (LLMs), where access to model weights and gradients is often constrained. We explore both black-box and white-box confidence estimation strategies, evaluating their effectiveness on cross-domain text-to-SQL benchmarks. Our evaluation highlights the superior performance of consistency-based methods among black-box models and the advantage of SQL-syntax-aware approaches for interpreting LLM logits in white-box settings. Furthermore, we show that execution-based grounding of queries provides a valuable supplementary signal, improving the effectiveness of both approaches.

Text-to-SQL translation enables non-expert users to query relational databases using natural language, with applications in education and business intelligence. This study evaluates three lightweight transformer models - T5-Small, BART-Small, and GPT-2 - on the Spider dataset, focusing on low-resource settings. We developed a reusable, model-agnostic pipeline that tailors schema formatting to each model's architecture, training them across 1000 to 5000 iterations and evaluating on 1000 test samples using Logical Form Accuracy (LFAcc), BLEU, and Exact Match (EM) metrics. Fine-tuned T5-Small achieves the highest LFAcc (27.8%), outperforming BART-Small (23.98%) and GPT-2 (20.1%), highlighting encoder-decoder models' superiority in schema-aware SQL generation. Despite resource constraints limiting performance, our pipeline's modularity supports future enhancements, such as advanced schema linking or alternative base models. This work underscores the potential of compact transformers for accessible text-to-SQL solutions in resource-scarce environments.

Estimating the confidence of large language model (LLM) outputs is essential for real-world applications requiring high user trust. Black-box uncertainty quantification (UQ) methods, relying solely on model API access, have gained popularity due to their practical benefits. In this paper, we examine the implicit assumption behind several UQ methods, which use generation consistency as a proxy for confidence, an idea we formalize as the consistency hypothesis. We introduce three mathematical statements with corresponding statistical tests to capture variations of this hypothesis and metrics to evaluate LLM output conformity across tasks. Our empirical investigation, spanning 8 benchmark datasets and 3 tasks (question answering, text summarization, and text-to-SQL), highlights the prevalence of the hypothesis under different settings. Among the statements, we highlight the `Sim-Any' hypothesis as the most actionable, and demonstrate how it can be leveraged by proposing data-free black-box UQ methods that aggregate similarities between generations for confidence estimation. These approaches can outperform the closest baselines, showcasing the practical value of the empirically observed consistency hypothesis.

Calibration is crucial as large language models (LLMs) are increasingly deployed to convert natural language queries into SQL for commercial databases. In this work, we investigate calibration techniques for assigning confidence to generated SQL queries. We show that a straightforward baseline -- deriving confidence from the model's full-sequence probability -- outperforms recent methods that rely on follow-up prompts for self-checking and confidence verbalization. Our comprehensive evaluation, conducted across two widely-used Text-to-SQL benchmarks and multiple LLM architectures, provides valuable insights into the effectiveness of various calibration strategies.

This study presents AraSpider, the first Arabic version of the Spider dataset, aimed at improving natural language processing (NLP) in the Arabic-speaking community. Four multilingual translation models were tested for their effectiveness in translating English to Arabic. Additionally, two models were assessed for their ability to generate SQL queries from Arabic text. The results showed that using back translation significantly improved the performance of both ChatGPT 3.5 and SQLCoder models, which are considered top performers on the Spider dataset. Notably, ChatGPT 3.5 demonstrated high-quality translation, while SQLCoder excelled in text-to-SQL tasks. The study underscores the importance of incorporating contextual schema and employing back translation strategies to enhance model performance in Arabic NLP tasks. Moreover, the provision of detailed methodologies for reproducibility and translation of the dataset into other languages highlights the research's commitment to promoting transparency and collaborative knowledge sharing in the field. Overall, these contributions advance NLP research, empower Arabic-speaking researchers, and enrich the global discourse on language comprehension and database interrogation.

This study investigates various approaches to using Large Language Models (LLMs) for Text-to-SQL program synthesis, focusing on the outcomes and insights derived. Employing the popular Text-to-SQL dataset, spider, the goal was to input a natural language question along with the database schema and output the correct SQL SELECT query. The initial approach was to fine-tune a local and open-source model to generate the SELECT query. After QLoRa fine-tuning WizardLM's WizardCoder-15B model on the spider dataset, the execution accuracy for generated queries rose to a high of 61%. With the second approach, using the fine-tuned gpt-3.5-turbo-16k (Few-shot) + gpt-4-turbo (Zero-shot error correction), the execution accuracy reached a high of 82.1%. Of all the incorrect queries, most can be categorized into a seven different categories of what went wrong: selecting the wrong columns or wrong order of columns, grouping by the wrong column, predicting the wrong values in conditionals, using different aggregates than the ground truth, extra or too few JOIN clauses, inconsistencies in the Spider dataset, and lastly completely incorrect query structure. Most if not all of the queries fall into these categories and it is insightful to understanding where the faults still lie with LLM program synthesis and where they can be improved.