Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs
Summary: Chatty-Gen: multi-stage retrieval-augmented platform to build domain-specific dialogue benchmarks from knowledge graphs. It uses stage-wise validation and efficient KG retrieval to curb hallucinations and cut costly LLM usage, beating baselines. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Reham Omar (Concordia University)
- 2. Omij Mangukiya (Concordia University)
- 3. Essam Mansour (Concordia University)
BibTeX Citation
@inproceedings{omar_sigmod25,
title = {{Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs}},
author = {Omar, Reham and Mangukiya, Omij and Mansour, Essam},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3709681},
url = {https://dl.acm.org/doi/10.1145/3709681},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,626 | Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs | 2026 | SIGMOD | 4.9793485e-05 |
| 10,815 | CRAFT: Corpus Relatedness Analysis Using Fourier Transforms | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 5,995 | Maestro: Automatic Generation of Comprehensive Benchmarks for Question Answering Over Knowledge Graphs | 2023 | SIGMOD | 5.9214708e-05 |
| 10,213 | A Universal Question-Answering Platform for Knowledge Graphs | 2023 | SIGMOD | 5.0596605e-05 |
Previous
Page 1 / 1
Next