Muhammad Imam Luthfi Balaka
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Muhammad Imam Luthfi Balaka has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Raul Castro Fernandez
The University of Chicago, Chicago, USA
3 shared publications - Adila Alfa Krisnadhi
University of Indonesia, Depok, Indonesia
1 shared publication - Danni Liu
Computer Science, The University of Chicago, Chicago, USA
1 shared publication - David Alexander
University of Indonesia, Depok, Indonesia
1 shared publication - Qiming Wang
The University of Chicago, Chicago, USA
1 shared publication - Yue Gong
The University of Chicago, Chicago, USA
1 shared publication
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
StepLens: Supporting Inspection and Evaluation in Agentic Tabular Data Work to Narrow Down the Gulf of Evaluation
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessStepLens: Supporting Inspection and Evaluation in Agentic Tabular Data Work to Narrow Down the Gulf of Evaluation
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1199-1203
Demonstration of Pneuma-Seeker: An Agentic System for Reifying and Fulfilling Information Needs on Tabular Data
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1199-1203
Open AccessDemonstration of Pneuma-Seeker: An Agentic System for Reifying and Fulfilling Information Needs on Tabular Data
- Open Access
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-28
Pneuma : Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
Finding relevant tables among databases, lakes, and repositories is the first step in extracting value from data. Such a task remains difficult because assessing whether a table is relevant to a problem does not always depend only on its content but also on the context, which is usually tribal knowledge known to the individual or team. While tools like data catalogs and academic data discovery systems target this problem, they rely on keyword search or more complex interfaces, limiting non-technical users' ability to find relevant data. The advent of large language models (LLMs) offers a unique opportunity for users to ask questions directly in natural language, making dataset discovery more intuitive, accessible, and efficient. In this paper, we introduce Pneuma , a retrieval-augmented generation (RAG) system designed to efficiently and effectively discover tabular data. Pneuma leverages large language models (LLMs) for both table representation and table retrieval. For table representation, Pneuma preserves schema and row-level information to ensure comprehensive data understanding. For table retrieval, Pneuma augments LLMs with traditional information retrieval techniques, such as full-text and vector search, harnessing the strengths of both to improve retrieval performance. To evaluate Pneuma , we generate comprehensive benchmarks that simulate table discovery workload on six real-world datasets including enterprise data, scientific databases, warehousing data, and open data. Our results demonstrate that Pneuma outperforms widely used table search systems (such as full-text search and state-of-the-art RAG systems) in accuracy and resource efficiency.
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-28
Open AccessPneuma : Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
Finding relevant tables among databases, lakes, and repositories is the first step in extracting value from data. Such a task remains difficult because assessing whether a table is relevant to a problem does not always depend only on its content but also on the context, which is usually tribal knowledge known to the individual or team. While tools like data catalogs and academic data discovery systems target this problem, they rely on keyword search or more complex interfaces, limiting non-technical users' ability to find relevant data. The advent of large language models (LLMs) offers a unique opportunity for users to ask questions directly in natural language, making dataset discovery more intuitive, accessible, and efficient. In this paper, we introduce Pneuma , a retrieval-augmented generation (RAG) system designed to efficiently and effectively discover tabular data. Pneuma leverages large language models (LLMs) for both table representation and table retrieval. For table representation, Pneuma preserves schema and row-level information to ensure comprehensive data understanding. For table retrieval, Pneuma augments LLMs with traditional information retrieval techniques, such as full-text and vector search, harnessing the strengths of both to improve retrieval performance. To evaluate Pneuma , we generate comprehensive benchmarks that simulate table discovery workload on six real-world datasets including enterprise data, scientific databases, warehousing data, and open data. Our results demonstrate that Pneuma outperforms widely used table search systems (such as full-text search and state-of-the-art RAG systems) in accuracy and resource efficiency.