AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xin, Amy, Liu, Jinxin, Yao, Zijun, Lee, Zhicheng, Cao, Shulin, Hou, Lei, Li, Juanzi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916970988830720
author Xin, Amy
Liu, Jinxin
Yao, Zijun
Lee, Zhicheng
Cao, Shulin
Hou, Lei
Li, Juanzi
author_facet Xin, Amy
Liu, Jinxin
Yao, Zijun
Lee, Zhicheng
Cao, Shulin
Hou, Lei
Li, Juanzi
contents Despite the outstanding capabilities of large language models (LLMs), knowledge-intensive reasoning still remains a challenging task due to LLMs' limitations in compositional reasoning and the hallucination problem. A prevalent solution is to employ chain-of-thought (CoT) with retrieval-augmented generation (RAG), which first formulates a reasoning plan by decomposing complex questions into simpler sub-questions, and then applies iterative RAG at each sub-question. However, prior works exhibit two crucial problems: inadequate reasoning planning and poor incorporation of heterogeneous knowledge. In this paper, we introduce AtomR, a framework for LLMs to conduct accurate heterogeneous knowledge reasoning at the atomic level. Inspired by how knowledge graph query languages model compositional reasoning through combining predefined operations, we propose three atomic knowledge operators, a unified set of operators for LLMs to retrieve and manipulate knowledge from heterogeneous sources. First, in the reasoning planning stage, AtomR decomposes a complex question into a reasoning tree where each leaf node corresponds to an atomic knowledge operator, achieving question decomposition that is highly fine-grained and orthogonal. Subsequently, in the reasoning execution stage, AtomR executes each atomic knowledge operator, which flexibly selects, retrieves, and operates atomic level knowledge from heterogeneous sources. We also introduce BlendQA, a challenging benchmark specially tailored for heterogeneous knowledge reasoning. Experiments on three single-source and two multi-source datasets show that AtomR outperforms state-of-the-art baselines by a large margin, with F1 score improvements of 9.4% on 2WikiMultihop and 9.5% on BlendQA. We release our code and datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16495
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Xin, Amy
Liu, Jinxin
Yao, Zijun
Lee, Zhicheng
Cao, Shulin
Hou, Lei
Li, Juanzi
Computation and Language
Despite the outstanding capabilities of large language models (LLMs), knowledge-intensive reasoning still remains a challenging task due to LLMs' limitations in compositional reasoning and the hallucination problem. A prevalent solution is to employ chain-of-thought (CoT) with retrieval-augmented generation (RAG), which first formulates a reasoning plan by decomposing complex questions into simpler sub-questions, and then applies iterative RAG at each sub-question. However, prior works exhibit two crucial problems: inadequate reasoning planning and poor incorporation of heterogeneous knowledge. In this paper, we introduce AtomR, a framework for LLMs to conduct accurate heterogeneous knowledge reasoning at the atomic level. Inspired by how knowledge graph query languages model compositional reasoning through combining predefined operations, we propose three atomic knowledge operators, a unified set of operators for LLMs to retrieve and manipulate knowledge from heterogeneous sources. First, in the reasoning planning stage, AtomR decomposes a complex question into a reasoning tree where each leaf node corresponds to an atomic knowledge operator, achieving question decomposition that is highly fine-grained and orthogonal. Subsequently, in the reasoning execution stage, AtomR executes each atomic knowledge operator, which flexibly selects, retrieves, and operates atomic level knowledge from heterogeneous sources. We also introduce BlendQA, a challenging benchmark specially tailored for heterogeneous knowledge reasoning. Experiments on three single-source and two multi-source datasets show that AtomR outperforms state-of-the-art baselines by a large margin, with F1 score improvements of 9.4% on 2WikiMultihop and 9.5% on BlendQA. We release our code and datasets.
title AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
topic Computation and Language
url https://arxiv.org/abs/2411.16495