%76%65%63%74%6f%72
-
KAIST Develops Next-Generation Database Technology That Reduces AI Hallucinations and Improves Accuracy by 78%
One of the greatest weaknesses of AI agents that read and understand vast amounts of enterprise data is “hallucination” — the generation of plausible-sounding but factually incorrect information. KAIST researchers have developed a next-generation database technology capable of understanding documents, data, and relationships among entities all at once. The technology improves AI response accuracy by up to 78% and processing speed by up to 20 times, addressing a key challenge in the commercialization of enterprise AI.
KAIST, led by President Kwang Hyung Lee, announced on the 19th that a research team led by Professor Min-Soo Kim of the School of Computing, in collaboration with faculty startup GraphAI Co., Ltd., has developed “AkasicDB,” a next-generation database technology that integrates the functions of vector databases, graph databases, and relational databases into a single database management system (DBMS). Based on this technology, the team also developed a new Retrieval-Augmented Generation (RAG) method called “Omni RAG.”
AkasicDB is designed to integrate and execute the functions of vector databases, which convert the meaning of documents or images into numerical vectors to search for similar information; graph databases, which store and analyze relationships among entities such as people, companies, and products; and relational databases, which systematically manage data in table form. Omni RAG, developed on this foundation, improves the accuracy of generative AI responses by simultaneously utilizing semantic information from documents, relationships among entities, and structured data.
AI agents have recently been spreading rapidly based on RAG technology, which searches vast collections of corporate documents and expert knowledge and generates responses based on the retrieved information. However, real-world enterprise data is distributed across various forms, including documents, tables, and relationships among entities, making it difficult for AI to comprehensively understand and use the data. As a result, AI may generate factually incorrect responses without sufficient grounding, creating hallucination issues that have been regarded as a major obstacle to the broader adoption of enterprise AI.
Conventional RAG typically works by converting user queries and documents into vectors, retrieving semantically similar documents, and providing them to a large language model (LLM), an AI model trained on massive datasets to generate human-like language. While this approach is effective for searching unstructured documents, it has limitations when handling complex queries that must also consider relationships among entities in documents or structured conditions such as specific periods, types, or ranges.
For example, a query such as, “Find clauses related to Company A among contracts signed last year, and explain how those clauses are connected to product supply issues,” requires vector search to identify document meaning, graph search to explore relationships among entities, and relational queries to filter by date and type. In existing systems, this required building multiple types of databases separately and combining the results at the application layer, leading to management complexity and response delays.
To solve this problem, the research team proposed Omni RAG, which integrates vector similarity search, graph traversal, and relational filtering within a single query and execution plan. Omni RAG identifies more accurate evidence by simultaneously utilizing semantic information from documents, relationship information from knowledge graphs, and structural conditions from tabular data, significantly reducing AI hallucinations.
AkasicDB, developed to support this method, adopts a new architecture that integrates graph databases, vector databases, and relational databases into a single engine. Users can express complex RAG queries that combine vector search, graph traversal, and relational filtering as a single SQL/GQL* query, and AkasicDB optimizes and processes the query as one unified execution plan.
SQL/GQL, or Structured Query Language/Graph Query Language, refers to command languages used to search or modify information stored in databases. SQL is the traditional language used to handle tabular data, while GQL is a language dedicated to graph data and is used to analyze connections among entities such as people, companies, and products.
Through this integrated architecture, AkasicDB minimizes unnecessary intermediate result generation and data movement, greatly reducing the number of tokens used by LLMs and shortening response latency. In experiments, complex search queries that took up to 21.3 seconds in existing systems were processed in under one second, achieving a performance improvement of more than 20 times. Omni RAG also improved response accuracy by up to 78% compared with conventional RAG. These results demonstrate its potential to substantially mitigate hallucination, one of the core challenges for enterprise AI agents.
Professor Min-Soo Kim said, “For AI agents to accurately understand and utilize the vast amounts of data held by enterprises, data infrastructure capable of processing vector, graph, and relational data in an integrated manner within a single system is essential. AkasicDB is a next-generation database technology for the era of AI agents, and we expect it to be used as core data infrastructure in fields requiring high reliability, including defense, manufacturing, finance, law, science, and technology.”
KAIST School of Computing Ph.D. student Geonho Lee participated in this research as the first author. The research results were presented as a demo paper on June 2 at ACM SIGMOD 2026, one of the world’s most prestigious international conferences in the field of databases, where they drew strong interest from global companies and researchers.
※ Paper title: AkasicDB: Demonstrating Omni RAG with a Unified Vector-Graph-Relational DBMS
DOI: https://doi.org/10.1145/3788853.3801609
※ Author information: Geonho Lee, KAIST, first author; Jeongho Park and Donghyoung Han, GraphAI Co., Ltd., co-authors; Professor Min-Soo Kim, KAIST, corresponding author
※ Demonstration video: https://www.youtube.com/watch?v=KD6MznZ61P4
2026.06.19 View 2679 -
KAIST Develops Janus-like Metasurface Technology that Acts According to the Direction of Light
Metasurface technology is an advanced optical technology that is thinner, lighter, and capable of precisely controlling light through nanometer-sized artificial structures compared to conventional technologies. KAIST researchers have overcome the limitations of existing metasurface technologies and successfully designed a Janus metasurface capable of perfectly controlling asymmetric light transmission. By applying this technology, they also proposed an innovative method to significantly enhance security by only decoding information under specific conditions.
KAIST (represented by President Kwang Hyung Lee) announced on the 15th of October that a research team led by Professor Jonghwa Shin from the Department of Materials Science and Engineering had developed a Janus metasurface capable of perfectly controlling asymmetric light transmission.
Asymmetric properties, which react differently depending on the direction, play a crucial role in various fields of science and engineering. The Janus metasurface developed by the research team implements an optical system capable of performing different functions in both directions.
Like the Roman god Janus with two faces, this metasurface shows entirely different optical responses depending on the direction of incoming light, effectively operating two independent optical systems with a single device (for example, a metasurface that acts as a magnifying lens in one direction and as a polarized camera in the other). In other words, by using this technology, it's possible to operate two different optical systems (e.g., a lens and a hologram) depending on the direction of the light.
This achievement addresses a challenge that existing metasurface technologies had not resolved. Conventional metasurface technology had limitations in selectively controlling the three properties of light—intensity, phase, and polarization—based on the direction of incidence.
The research team proposed a solution based on mathematical and physical principles, and succeeded in experimentally implementing different vector holograms in both directions. Through this achievement, they showcased a complete asymmetric light transmission control technology.
< Figure 1. Schematics of a device featuring asymmetric transmission. a) Device operating as a magnifying lens for back-side illumination. b) Device operating as a polarization camera for front-side illumination. >
Additionally, the research team developed a new optical encryption technology based on this metasurface technology. By using the Janus metasurface, they implemented a vector hologram that generates different images depending on the direction and polarization state of incoming light, showcasing an optical encryption system that significantly enhances security by allowing information to be decoded only under specific conditions.
This technology is expected to serve as a next-generation security solution, applicable in various fields such as quantum communication and secure data transmission.
Furthermore, the ultra-thin structure of the metasurface is expected to significantly reduce the volume and weight of traditional optical devices, contributing greatly to the miniaturization and lightweight design of next-generation devices.
< Figure 2. Experimental demonstration of Janus vectorial holograms. With front illuminations, vector images of the butterfly and the grasshopper are created, and with the back-side illuminations, vector images of the ladybug and the beetle are created. >
Professor Jonghwa Shin from the Department of Materials Science and Engineering at KAIST stated, "This research has enabled the complete asymmetric transmission control of light’s intensity, phase, and polarization, which has been a long-standing challenge in optics. It has opened up the possibility of developing various applied optical devices." He added, "We plan to continue developing optical devices that can be applied to various fields such as augmented reality (AR), holographic displays, and LiDAR systems for autonomous vehicles, utilizing the full potential of metasurface technology."
This research, in which Hyeonhee Kim (a doctoral student in the Department of Materials Science and Engineering at KAIST) and Joonkyo Jung participated as co-first authors, was published online in the international journal Advanced Materials and is scheduled to be published in the October 31 issue. (Title of the paper: "Bidirectional Vectorial Holography Using Bi-Layer Metasurfaces and Its Application to Optical Encryption")
The research was supported by the Nano Materials Technology Development Program and the Mid-Career Researcher Program of the National Research Foundation of Korea.
2024.10.15 View 10426