RuAG: Learned-rule-augmented Generation for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yudi, Xiao, Pei, Wang, Lu, Zhang, Chaoyun, Fang, Meng, Du, Yali, Puzyrev, Yevgeniy, Yao, Randolph, Qin, Si, Lin, Qingwei, Pechenizkiy, Mykola, Zhang, Dongmei, Rajmohan, Saravan, Zhang, Qi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912106807296000
author Zhang, Yudi
Xiao, Pei
Wang, Lu
Zhang, Chaoyun
Fang, Meng
Du, Yali
Puzyrev, Yevgeniy
Yao, Randolph
Qin, Si
Lin, Qingwei
Pechenizkiy, Mykola
Zhang, Dongmei
Rajmohan, Saravan
Zhang, Qi
author_facet Zhang, Yudi
Xiao, Pei
Wang, Lu
Zhang, Chaoyun
Fang, Meng
Du, Yali
Puzyrev, Yevgeniy
Yao, Randolph
Qin, Si
Lin, Qingwei
Pechenizkiy, Mykola
Zhang, Dongmei
Rajmohan, Saravan
Zhang, Qi
contents In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, RuAG applies Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03349
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RuAG: Learned-rule-augmented Generation for Large Language Models
Zhang, Yudi
Xiao, Pei
Wang, Lu
Zhang, Chaoyun
Fang, Meng
Du, Yali
Puzyrev, Yevgeniy
Yao, Randolph
Qin, Si
Lin, Qingwei
Pechenizkiy, Mykola
Zhang, Dongmei
Rajmohan, Saravan
Zhang, Qi
Artificial Intelligence
Computation and Language
Machine Learning
In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, RuAG applies Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.
title RuAG: Learned-rule-augmented Generation for Large Language Models
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.03349