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

📅 2026-01-10
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the challenge of multi-hop question answering over hybrid table-text data, where retrieval noise significantly degrades performance and conventional RAG approaches struggle to model reasoning chains due to their flat document representation. The authors propose the first zero-shot graph-based framework that leverages large language models to dynamically construct an evidence graph from noisy retrieval results—treating documents as nodes and semantic relations as edges—to explicitly capture multi-hop reasoning paths and automatically identify bridging documents. Requiring no task-specific training, the method achieves 48.80 EM on OTT-QA, outperforming strong baselines by 19.9 points, matching the performance of fine-tuned retrieval models (CORE: 49.0 EM), and approaching that of the state-of-the-art system (COS: 56.9 EM).

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

multi-hop question answering
table-text QA
retrieval noise
reasoning chains
evidence retrieval
Innovation

Methods, ideas, or system contributions that make the work stand out.

graph-based reasoning
zero-shot QA
evidence graph
multi-hop question answering
retrieval-augmented generation
💼 Related Jobs
No related jobs found.
M
Mohamed Sharafath
Comcast India Engineering Center, Chennai, India
A
Aravindh Annamalai
Comcast India Engineering Center, Chennai, India
G
Ganesh Murugan
Comcast, Philadelphia, United States
A
Aravindakumar Venugopalan
Comcast, Philadelphia, United States