Related papers: Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering

Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering

URL: http://arxiv.org/abs/2407.09506v1
Date: Fri, 14 Jun 2024 13:28:03 GMT
Title: Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering
Authors: Parag Jain, Mirella Lapata,
Abstract summary: 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.
Score: 58.17090503446995
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models [33.662269036173456]
Large Language Models (LLMs) may suffer from hallucinations in real-world applications due to the lack of relevant knowledge. Knowledge Graph Question Answering (KGQA) serves as a critical touchstone for the integration. We propose an interactive KGQA framework that leverages the interactive learning capabilities of LLMs to perform reasoning and Debating over Graphs (DoG)
arXiv Detail & Related papers (2024-09-05T01:11:58Z)
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering [61.93058781222079]
We develop a flexible question-answering framework targeting real-world textual graphs. We introduce the first retrieval-augmented generation (RAG) approach for general textual graphs. G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem.
arXiv Detail & Related papers (2024-02-12T13:13:04Z)
GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models [33.56759621666477]
We present a benchmark dataset for evaluating the integration of graph knowledge into language models. The proposed dataset is designed to evaluate graph-language models' ability to understand graphs and make use of it for answer generation. We perform experiments with language-only models and the proposed graph-language model to validate the usefulness of the paired graphs and to demonstrate the difficulty of the task.
arXiv Detail & Related papers (2023-10-12T16:46:58Z)
Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation [23.54754465832362]
In conventional graph neural networks (GNNs) message passing on a graph is independent from text. This training regime leads to a semantic gap between graph knowledge and text. We propose a novel framework for knowledge graph enhanced dialogue generation.
arXiv Detail & Related papers (2023-06-28T13:21:00Z)
Conversational Semantic Parsing using Dynamic Context Graphs [68.72121830563906]
We consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types. We focus on models which are capable of interactively mapping user utterances into executable logical forms.
arXiv Detail & Related papers (2023-05-04T16:04:41Z)
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering [159.9645181522436]
GreaseLM is a new model that fuses encoded representations from pretrained LMs and graph neural networks over multiple layers of modality interaction operations. We show that GreaseLM can more reliably answer questions that require reasoning over both situational constraints and structured knowledge, even outperforming models 8x larger.
arXiv Detail & Related papers (2022-01-21T19:00:05Z)
Ontology-based question answering over corporate structured data [0.0]
Ontology-based approach to the Natural Language Understanding (NLU) processing allows to improve questions answering quality in dialogue systems. We describe our NLU engine architecture and evaluate its implementation. We describe the dialogue engine for a chat bot which can keep the conversation context and ask clarifying questions.
arXiv Detail & Related papers (2021-11-08T13:49:15Z)
Graph-based Multi-hop Reasoning for Long Text Generation [66.64743847850666]
MRG consists of twoparts, a graph-based multi-hop reasoning module and a path-aware sentence realization module. Unlike previous black-box models, MRG explicitly infers the skeleton path, which provides explanatory views tounderstand how the proposed model works.
arXiv Detail & Related papers (2020-09-28T12:47:59Z)
Iterative Context-Aware Graph Inference for Visual Dialog [126.016187323249]
We propose a novel Context-Aware Graph (CAG) neural network. Each node in the graph corresponds to a joint semantic feature, including both object-based (visual) and history-related (textual) context representations.
arXiv Detail & Related papers (2020-04-05T13:09:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.