dorsal/arxiv
View SchemaN2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs
| Authors | Mohamed Sharafath, Aravindh Annamalai, Ganesh Murugan, Aravindakumar Venugopalan |
|---|---|
| Categories | |
| ArXiv ID | 2601.06603vv1 |
| URL | https://arxiv.org/abs/2601.06603 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora, but standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked lists, causing retrieval noise to obscure reasoning chains. We introduce N2N-GQA. To our knowledge, it is the first zeroshot framework for open-domain hybrid table-text QA that constructs dynamic evidence graphs from noisy retrieval outputs. Our key insight is that multi-hop reasoning requires understanding relationships between evidence pieces: by modeling documents as graph nodes with semantic relationships as edges, we identify bridge documents connecting reasoning steps, a capability absent in list-based retrieval. On OTT-QA, graph-based evidence curation provides a 19.9-point EM improvement over strong baselines, demonstrating that organizing retrieval results as structured graphs is critical for multihop reasoning. N2N-GQA achieves 48.80 EM, matching finetuned retrieval models (CORE: 49.0 EM) and approaching heavily optimized systems (COS: 56.9 EM) without any task specific training. This establishes graph-structured evidence organization as essential for scalable, zero-shot multi-hop QA systems and demonstrates that simple, interpretable graph construction can rival sophisticated fine-tuned approaches.
{
"annotation_id": "88aa028b-f599-4f64-a94e-155d45376434",
"date_created": "2026-02-17T05:53:07.774000Z",
"date_modified": "2026-02-17T05:53:07.774000Z",
"file_hash": "9912a6d8b14ef0f7aee3af90a125d139ff1bbe9f7b48e94676a935c7e5f60a64",
"private": false,
"record": {
"abstract": "Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora, but standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked lists, causing retrieval noise to obscure reasoning chains. We introduce N2N-GQA. To our knowledge, it is the first zeroshot framework for open-domain hybrid table-text QA that constructs dynamic evidence graphs from noisy retrieval outputs. Our key insight is that multi-hop reasoning requires understanding relationships between evidence pieces: by modeling documents as graph nodes with semantic relationships as edges, we identify bridge documents connecting reasoning steps, a capability absent in list-based retrieval. On OTT-QA, graph-based evidence curation provides a 19.9-point EM improvement over strong baselines, demonstrating that organizing retrieval results as structured graphs is critical for multihop reasoning. N2N-GQA achieves 48.80 EM, matching finetuned retrieval models (CORE: 49.0 EM) and approaching heavily optimized systems (COS: 56.9 EM) without any task specific training. This establishes graph-structured evidence organization as essential for scalable, zero-shot multi-hop QA systems and demonstrates that simple, interpretable graph construction can rival sophisticated fine-tuned approaches.",
"arxiv_id": "2601.06603",
"authors": [
"Mohamed Sharafath",
"Aravindh Annamalai",
"Ganesh Murugan",
"Aravindakumar Venugopalan"
],
"categories": [
"cs.CL"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs",
"url": "https://arxiv.org/abs/2601.06603",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "a5aaaba4-a3e0-4669-a9c0-27988cfbdd29",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}