Bird
PulseAugur coverage of Bird — every cluster mentioning Bird across labs, papers, and developer communities, ranked by signal.
- instance of web crawler 90%
- developed Text To Sql 90%
- instance of DagsHub 90%
- instance of CatalyzeX 90%
- instance of Gotit.pub 90%
- instance of schemagate 90%
- instance of ScienceCast 90%
- used by schemagate 80%
- instance of Text To Sql 70%
- used by Text To Sql 70%
- uses Text-to-SQL for Korean Language based on Multilingual BERT 70%
- instance of Text-to-SQL for Korean Language based on Multilingual BERT 70%
12 day(s) with sentiment data
-
New methods FERN and NIFT-SQL enhance Text-to-SQL table retrieval
Researchers have developed two new methods, FERN and NIFT-SQL, to improve table retrieval for Text-to-SQL systems. FERN utilizes frozen retrievers and a learned ranking model to identify relevant tables, achieving high …
-
VCoT-SQL framework boosts open-source LLMs for Text-to-SQL tasks
Researchers have developed VCoT-SQL, a novel framework designed to enhance the Text-to-SQL generation capabilities of open-source large language models. This approach addresses the limitations of existing methods by inc…
-
New GRIPS method boosts Text-to-SQL accuracy by 11.8% with reduced token usage
Researchers have developed GRIPS, a three-stage method to improve Text-to-SQL systems by explicitly grounding question mentions to tables, columns, values, and relations before SQL generation. This approach addresses a …
-
AI system uses cameras to deter wildlife from railway tracks in Sweden
A new AI-powered system is being deployed in Sweden to prevent wildlife from causing train accidents. Developed by Flox Intelligence in partnership with Alstom, the system uses cameras to identify animals like elk, bird…
-
New benchmark SpecBridge reveals text-to-SQL models make hidden choices
A new benchmark called SpecBridge has been developed to identify instances where text-to-SQL models make implicit choices without explicit user instruction. These models can provide a plausible numerical answer that dif…
-
VIDRAFT's NL2SQL Engine Outperforms BIRD Mini-Dev Benchmark
VIDRAFT's Darwin-180B-NL2SQL system has achieved a score of 83.80% on the BIRD Mini-Dev benchmark, surpassing the current top-ranked entry. This text-to-SQL engine, utilizing the Darwin-180B-RSI model without fine-tunin…
-
Developer's schemagate library outperforms other methods for text-to-SQL table selection
A developer compared four methods for selecting relevant database tables for text-to-SQL prompts, finding that their open-source library, schemagate, significantly outperformed other approaches. Using the same MiniLM mo…
-
Claude Opus 5.5 achieves 77.1% on BIRD text-to-SQL benchmark with single query
A developer has achieved a 77.1% execution accuracy on the BIRD text-to-SQL benchmark using a single model call per question with Claude Opus 5.5. This approach, implemented via the schemagate system, involves the model…
-
Gemini 2.5 Flash beats Claude Sonnet 4.5 on Oracle Text-to-SQL benchmark
A new benchmark called UniQL, designed to translate natural language questions into SQL queries across various dialects, has highlighted the performance differences between large language models. On the Oracle dialect o…
-
Schemagate outperforms new Text-to-SQL access control benchmark
A new benchmark for Text-to-SQL systems, released by a SIGMOD'27 paper, reveals that simply hiding restricted columns still allows models to answer questions they should refuse. The benchmark, named BIRD, showed that mo…
-
LLM reranker bug fixed, boosting text-to-SQL accuracy
A developer discovered a bug in their LLM reranker for the schemagate text-to-SQL tool where the model was being called but not providing answers due to token limits, causing the system to silently fall back to a less e…
-
New research tackles Text-to-SQL reliability with premise critique and evidence-guided plans
Two new research papers introduce novel frameworks for improving the reliability and transparency of Text-to-SQL systems. PremiseSQL focuses on enabling these systems to recognize and abstain from generating SQL for que…
-
Text-to-SQL confidence scores show improved accuracy on Spider dataset
A new research paper explores the effectiveness of confidence scores in Text-to-SQL systems, specifically evaluating GPT-5.1 on the BIRD and Spider datasets. The study found that a designed confidence score performed we…
-
New Ownership-Aware Routing boosts LLM agent table queries
Researchers have developed a new method called Ownership-Aware Routing (OAR) to improve how Large Language Model (LLM) agents query siloed tables within organizations. Traditional "fan-out" (querying all owners simultan…
-
Bird CEO: AI Empowers Generalist Workers
The CEO of Bird, Robert Vis, believes that artificial intelligence is enhancing the capabilities of "high-agency" generalist employees. He suggests that AI tools allow these workers to operate more independently and eff…
-
Aura app uses tokenization to protect customer data for AI agents
A new desktop application called Aura has been developed to address the challenge of using AI agents with sensitive customer data. Aura employs a pseudonymization technique, replacing personal identifiers like names and…
-
New HSAD method improves LLM agent performance with advisor models
Researchers have developed a new method called Hindsight Structured Advice Distillation (HSAD) to improve the performance of large language model agents. HSAD uses a smaller "advisor" model to generate specific guidance…
-
New AptMQL-Bench benchmark highlights challenges in text-to-MQL generation
Researchers have developed AptMQL-Bench, a new benchmark for text-to-MQL generation, designed to improve natural language querying of document databases like MongoDB. Existing methods for converting text-to-SQL benchmar…
-
New Text-to-SQL system FLINT tackles complex financial data
Researchers have developed FLINT, a specialized Text-to-SQL system designed to handle complex financial data, which often uses opaque integer keys instead of human-readable strings. FLINT improves query accuracy by inco…
-
Business glossary boosts text-to-SQL agent accuracy, learned terms fail
A text-to-SQL agent's performance significantly improved when provided with a comprehensive business glossary, demonstrating a 28-question gain in accuracy compared to using no glossary. However, a glossary that was aut…