7 citations · 12 across the 15 of their papers we have counts for
16 papers
Explore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries
Anna Mazhar, Seiji Maekawa, Nikita Bhutani
Large language model agents must discover relevant tools from large libraries, e.g., thousands of tools, as new needs arise during task execution. When several candidates could sat…
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 Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval
Seiji Maekawa, Moin Aminnaseri, Pouya Pezeshkpour +1
Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collections. While stronger embedders can bet…
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…
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…
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…
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-
Chihiro Taguchi, Seiji Maekawa, Nikita Bhutani
Retrieval-augmented generation (RAG) and long-context language models (LCLMs) both address context limitations of LLMs in open-domain question answering (QA). However, optimal exte…
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
Catarina G. Belem, Pouya Pezeshkpour, Hayate Iso +3
Although many studies have investigated and reduced hallucinations in large language models (LLMs) for single-document tasks, research on hallucination in multi-document summarizat…
Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
Seiji Maekawa, Hayate Iso, Nikita Bhutani
The rapid increase in textual information means we need more efficient methods to sift through, organize, and understand it all. While retrieval-augmented generation (RAG) models e…
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models
Seiji Maekawa, Hayate Iso, Sairam Gurajada +1
While large language models (LMs) demonstrate remarkable performance, they encounter challenges in providing accurate responses when queried for information beyond their pre-traine…
A Simple and Scalable Graph Neural Network for Large Directed Graphs
Seiji Maekawa, Yuya Sasaki, Makoto Onizuka
Node classification is one of the hottest tasks in graph analysis. Though existing studies have explored various node representations in directed and undirected graphs, they have o…
GNN Transformation Framework for Improving Efficiency and Scalability
Seiji Maekawa, Yuya Sasaki, George Fletcher +1
We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our…
Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs
Seiji Maekawa, Koki Noda, Yuya Sasaki +1
Graph Neural Networks (GNNs) have achieved great success on a node classification task. Despite the broad interest in developing and evaluating GNNs, they have been assessed with l…
GenCAT: Generating Attributed Graphs with Controlled Relationships between Classes, Attributes, and Topology
Seiji Maekawa, Yuya Sasaki, George Fletcher +1
Generating large synthetic attributed graphs with node labels is an important task to support various experimental studies for graph analysis methods. Existing graph generators fai…
Non-linear Attributed Graph Clustering by Symmetric NMF with PU Learning
Seiji Maekawa, Koh Takeuch, Makoto Onizuka
We consider the clustering problem of attributed graphs. Our challenge is how we can design an effective and efficient clustering method that precisely captures the hidden relation…