# N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs

Source: [N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs](<https://www.sota2.com/research/paper/6965d1676343fa78c832337b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-14T05:00:04.658Z

Authors: Mohamed Sharafath, Aravindh Annamalai, Ganesh Murugan, Aravindakumar Venugopalan

Published: 2026-01-10T15:55:15.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-hop Question Answering on OTT-QA sampled 500 questions (val)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-ott-qa-sampled-500-questions-val.md>): Multi-hop Question Answering; OTT-QA sampled 500 questions (val); EM: 48.8.

- [Multi-hop Question Answering on OTT-QA full (val)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-ott-qa-full-val.md>): Multi-hop Question Answering; OTT-QA full (val); EM: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.06603>)

[PDF](<https://arxiv.org/pdf/2601.06603.pdf>)