A LLM powered system is presented for generating formally verified code for structured data translation between JSON schema of a pulse oximeter and FHIR format in Medical IoT.

This paper explores the integration of several extensions for Natural Language to SQL (NL2SQL) translation, including NatSQL representation, preprocessing, fine-tuning, and reranker model.

The authors introduce Structured PubMed, a comprehensive corpus of section-labeled biomedical abstracts compiled from the complete PubMed database.

The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…

SpecDB is a novel system that uses LLMs to synthesize highly customized, purpose-built relational databases, achieving performance comparable to commercial systems while significantly reducing code si…

This paper presents a study on improving healthcare-domain translation for four low-resource languages using Arabic and Persian as pivots, and introduces three transfer strategies.

The paper introduces DataOrchestra, a framework for example-specific processing of pretraining data for Large Language Models, achieving stable gains and reducing compute.

This paper introduces structured cut sets, a novel preprocessing technique for Maximum k-Cut, and extends existing techniques from Maximum Cut. The rules are optimality-preserving and yield significan…

This paper introduces a pipeline to extract grammatical rules, example sentences, and lexicons from grammar books and generates synthetic parallel corpora for fine-tuning machine translation models on…

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

This paper formalizes token optimization as a multi-objective constrained transformation problem for LLM-based Oracle-to-PostgreSQL migration, demonstrating that adaptive routing offers the best balan…

This paper investigates the performance of BEACON, a state-of-the-art method for low-resource, domain-aware Entity Matching, under varying algorithmic choices and data availability conditions.

The paper introduces XLGoBench, a synthetic benchmark of algorithmic tasks designed to detect persistent cross-lingual skill gaps in large language models.

The paper introduces OpenSTBench, a unified, multidimensional evaluation framework designed to comprehensively compare heterogeneous speech translation systems by jointly assessing translation, speech…

This paper introduces SkMTEB, a comprehensive text embedding benchmark for Slovak, and develops efficient, locally-deployable Slovak embeddings.

The paper proposes an aggressive, parameter-efficient method to prune non-essential experts from Mixture-of-Experts (MoE) LLMs, significantly compressing the model while maintaining high machine trans…