Skill Learning Using Process Mining for Large Language Model Plan Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Redis, Andrei Cosmin, Sani, Mohammadreza Fani, Zarrin, Bahram, Burattin, Andrea
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912075065851904
author Redis, Andrei Cosmin
Sani, Mohammadreza Fani
Zarrin, Bahram
Burattin, Andrea
author_facet Redis, Andrei Cosmin
Sani, Mohammadreza Fani
Zarrin, Bahram
Burattin, Andrea
contents Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is crucial for improving the efficiency and interpretability of plan generation as LLMs become more central to automation and decision-making. We introduce a novel approach to skill learning in LLMs by integrating process mining techniques, leveraging process discovery for skill acquisition, process models for skill storage, and conformance checking for skill retrieval. Our methods enhance text-based plan generation by enabling flexible skill discovery, parallel execution, and improved interpretability. Experimental results suggest the effectiveness of our approach, with our skill retrieval method surpassing state-of-the-art accuracy baselines under specific conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12870
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Skill Learning Using Process Mining for Large Language Model Plan Generation
Redis, Andrei Cosmin
Sani, Mohammadreza Fani
Zarrin, Bahram
Burattin, Andrea
Computation and Language
Artificial Intelligence
Databases
Emerging Technologies
Machine Learning
Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is crucial for improving the efficiency and interpretability of plan generation as LLMs become more central to automation and decision-making. We introduce a novel approach to skill learning in LLMs by integrating process mining techniques, leveraging process discovery for skill acquisition, process models for skill storage, and conformance checking for skill retrieval. Our methods enhance text-based plan generation by enabling flexible skill discovery, parallel execution, and improved interpretability. Experimental results suggest the effectiveness of our approach, with our skill retrieval method surpassing state-of-the-art accuracy baselines under specific conditions.
title Skill Learning Using Process Mining for Large Language Model Plan Generation
topic Computation and Language
Artificial Intelligence
Databases
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2410.12870