不微调大模型，用混合图结构提升表格与文本联合问答效果
Hybrid Graphs for Table-and-Text based Question Answering using LLMs
- 构建表格与文本的统一混合图，按问题剪枝信息
- 零样本下在两个数据集上分别提升10%和5.4%准确率
- 适合无需微调、追求高效推理的多源问答场景
回答需跨结构化（表格）和非结构化（文本）数据进行推理与聚合的问题仍具挑战。现有方法依赖微调和高质量人工标注数据，获取困难。大语言模型（LLMs）在单源文本多跳问答中已展示零样本潜力，但对多源表-文问答研究有限。本文提出一种基于混合图的表-文问答新方法，不需微调即可利用LLMs。该方法从文本和表格数据构建统一混合图，并根据输入问题剪枝信息，向LLM提供简洁相关上下文。我们在挑战性数据集Hybrid-QA和OTT-QA上评估，使用GPT-3.5、GPT-4和LLaMA-3等先进LLMs。该方法在两个数据集上均取得最佳零样本性能，分别将精确匹配分数提升10%和5.4%。此外，相比原始上下文，该方法可减少高达53%的令牌使用量。
原文摘要 · Abstract (English)
Answering questions that require reasoning and aggregation across both structured (tables) and unstructured (raw text) data sources presents significant challenges. Current methods rely on fine-tuning and high-quality, human-curated data, which is difficult to obtain. Recent advances in Large Language Models (LLMs) have shown promising results for multi-hop question answering (QA) over single-source text data in a zero-shot setting, yet exploration into multi-source Table-Text QA remains limited. In this paper, we present a novel Hybrid Graph-based approach for Table-Text QA that leverages LLMs without fine-tuning. Our method constructs a unified Hybrid Graph from textual and tabular data, pruning information based on the input question to provide the LLM with relevant context concisely. We evaluate our approach on the challenging Hybrid-QA and OTT-QA datasets using state-of-the-art LLMs, including GPT-3.5, GPT-4, and LLaMA-3. Our method achieves the best zero-shot performance on both datasets, improving Exact Match scores by up to 10% on Hybrid-QA and 5.4% on OTT-QA. Moreover, our approach reduces token usage by up to 53% compared to the original context.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。