Hugging Face Trending Papers June 29, 2026

How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD

Read the original on Hugging Face Trending Papers →

Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute? We answer with an honest, fully reproducible benchmark on the BIRD development split (n=1534, Execution Accuracy), evaluating three open model families across two generations -- Qwen2.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jun 30

How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD

arXiv:2606. 29733v1 Announce Type: cross Abstract: Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute?

By Vladimir Beskorovainyi

llms rag benchmarks data-engineering

arXiv AI

Jul 9

What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study

arXiv:2607. 06799v1 Announce Type: cross Abstract: Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference.

By Robert Richardson

llms fine-tuning benchmarks data-engineering

arXiv AI

Jul 29

How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

arXiv:2607. 25583v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore.

By Mahendra Singh Rathor, Anagheem Azzam

llms fine-tuning efficiency benchmarks data-engineering

arXiv AI

6d ago

DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

arXiv:2608. 11889v1 Announce Type: cross Abstract: Prompting-based (\textit{i}.

By Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma

llms fine-tuning benchmarks safety data-engineering

arXiv AI

Jun 9

PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems

arXiv:2606. 08481v1 Announce Type: cross Abstract: Enterprise property graphs vary widely in schema structure, internal terminology, domain assumptions, governance constraints, and user interaction patterns.

By Suraj Ranganath, Anish Raghavendra

llms agents benchmarks

arXiv AI

Jun 9

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

arXiv:2606. 08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale.

By Donghao Huang, Tomas Drietomsky, Benjamin Barrett, Zhaoxia Wang

llms fine-tuning efficiency benchmarks

Related stories

How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD

What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study

How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions