融合大语言模型与基于图的推理的对话式问答
Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering
AI总结：
针对对话式问答的上下文理解与多源证据推理难题，提出融合图结构表示与大语言模型的方法，通过注入图嵌入、增设记忆模块，在ConvMix基准上验证了推理能力与抗噪鲁棒性的提升。
摘要：
我们聚焦于对话式问答任务，该任务兼具上下文语境下的问题理解，以及对从文本、知识图谱、表格、信息框等异构来源收集的证据进行推理的双重挑战。我们的方法利用图结构表示来聚合问题及其上下文（即截至当前的对话内容、为寻找答案检索到的证据）的相关信息，同时发挥大语言模型（LLM）的推理与文本生成能力。图嵌入直接注入LLM，绕过词元嵌入层，并通过最小化交叉熵进行端到端学习。我们的模型设有一个记忆模块，用于跟踪和更新过往证据，从而随对话演进调整图的结构。在ConvMix基准（Christmann等人，2022a）上的实验结果表明，图嵌入提升了LLM的推理能力，而记忆模块则增强了模型对噪声与检索错误的鲁棒性。
英文摘要：
We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our method utilizes a graph structured representation to aggregate information about a question and its context (i.e., the conversation so far and evidence retrieved to find an answer), while also harnessing the reasoning and text generation capabilities of large language models (LLMs). Graph embeddings are directly injected into the LLM, bypassing the token embedding layers, and learned end-to-end by minimizing cross-entropy. Our model maintains a memory module to track and update past evidence, thus influencing the graph's structure, as the conversation evolves. Experimental results on the ConvMix benchmark(Christmann et al., 2022a) show that graph embeddings enhance the LLM's ability to reason, while the memory module provides robustness against noise and retrieval errors.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
