To Answer or Not to Answer (TAONA): A Robust Textual Graph Understanding and Question Answering Approach
Yuchen Yan, Aakash Kolekar, Sahika Genc, Wenju Xu, Edward W Huang, Anirudh Srinivasan, Mukesh Jain, Qi He
Abstract
Recently, textual graph-based retrieval-augmented generation (GraphRAG) has gained popularity for addressing hallucinations in large language models when answering domain-specific questions. Most existing studies assume that generated answers should comprehensively integrate all relevant information from the textual graph. However, this assumption may not always hold when certain information needs to be vetted or even blocked (e.g., due to safety concerns). In this paper, we target two sides of textual graph understanding and question answering: (1) normal question Answering (A-side): following standard practices, this task generates accurate responses using all relevant information within the textual graph; and (2) Blocked question answering (B-side): A new paradigm where the GraphRAG model must effectively infer and exclude specific relevant information in the generated response. To address these dual tasks, we propose TAONA, a novel GraphRAG model with two variants: (1) TAONA-A for A-side task, which incorporates a specialized GraphEncoder to learn graph prompting vectors; and (2) TAONA-B for B-side task, employing semi-supervised node classification to infer potential blocked graph nodes. Extensive experiments validate TAONA’s superior performance for both A-side and B-side tasks.
BibTeX
@inproceedings{emnlp2025_toanswerornottoa,
title = {To Answer or Not to Answer (TAONA): A Robust Textual Graph Understanding and Question Answering Approach},
author = {Yuchen Yan and Aakash Kolekar and Sahika Genc and Wenju Xu and Edward W Huang and Anirudh Srinivasan and Mukesh Jain and Qi He and Hanghang Tong},
booktitle = {EMNLP 2025},
year = {2025}
}