7 papers
Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews
Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo +13
Systematic literature reviews (SLRs) are a demanding and high-stakes form of scientific knowledge synthesis that remains underspecified as an evaluation setting for large language…
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Åukasz Borchmann, Jordy Van Landeghem, MichaÅ Turski +12
Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoni…
Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
Zhewei Yao, Guoheng Sun, Lukasz Borchmann +7
Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language…
Language Models Model Language
Åukasz Borchmann
Linguistic commentary on LLMs, heavily influenced by the theoretical frameworks of de Saussure and Chomsky, is often speculative and unproductive. Critics challenge whether LLMs ca…
Unchecked and Overlooked: Addressing the Checkbox Blind Spot in Large Language Models with CheckboxQA
MichaÅ Turski, Mateusz ChiliÅski, Åukasz Borchmann
Checkboxes are critical in real-world document processing where the presence or absence of ticks directly informs data extraction and decision-making processes. Yet, despite the st…
Query and Conquer: Execution-Guided SQL Generation
Åukasz Borchmann, Marek Wydmuch
We propose a novel approach for generating complex outputs that significantly improves accuracy in text-to-SQL tasks. Our method leverages execution results to select the most sema…