9 papers
From Textual Columns to Query Plans: A Unified Relational-Semantic Execution Framework for Hybrid Query Processing
Nima Shahbazi, Seiji Maekawa, Nikita Bhutani +1
Real-world table question answering often involves hybrid schemas in which some query-relevant information is explicit in relational columns, while other attributes, predicates, or…
Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications
Moin Aminnaseri, Farima Fatahi Bayat, Nikita Bhutani +17
NL2SQL systems aim to address the growing need for natural language interaction with data. However, real-world information rarely maps to a single SQL query because (1) users expre…
Align then Train: Efficient Retrieval Adapter Learning
Seiji Maekawa, Moin Aminnaseri, Pouya Pezeshkpour +1
Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while…
Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling
Seiji Maekawa, Jackson Hassell, Pouya Pezeshkpour +2
Existing benchmarks for tool-augmented language models (TaLMs) lack fine-grained control over task difficulty and remain vulnerable to data contamination. We present FuncBenchGen,…
Same Content, Different Representations: A Controlled Study for Table QA
Yue Zhang, Seiji Maekawa, Nikita Bhutani
Table Question Answering (Table QA) in real-world settings must operate over both structured databases and semi-structured tables containing textual fields. However, existing bench…
The Rarity Blind Spot: A Framework for Evaluating Statistical Reasoning in LLMs
Seiji Maekawa, Hayate Iso, Nikita Bhutani
Effective decision-making often relies on identifying what makes each candidate distinctive. While existing benchmarks for LLMs emphasize retrieving or summarizing information rele…