SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xiaochen, He, Junqing, Chen, Liang, Yang, Reza Haf Zhe, Wang, Yiru, Meng, Xiangdi, Pan, Kunhao, Sui, Zhifang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916448871383040
author Wang, Xiaochen
He, Junqing
Chen, Liang
Yang, Reza Haf Zhe
Wang, Yiru
Meng, Xiangdi
Pan, Kunhao
Sui, Zhifang
author_facet Wang, Xiaochen
He, Junqing
Chen, Liang
Yang, Reza Haf Zhe
Wang, Yiru
Meng, Xiangdi
Pan, Kunhao
Sui, Zhifang
contents Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. However, Multi-hop Question Answering (MHQA) remains challenging for many existing models due to issues like hallucination, error propagation, and limited context length. To address these challenges and enhance LLMs' performance on MHQA, we propose the Self-Guiding prompting Finite State Machine (SG-FSM), designed to strengthen multi-hop reasoning abilities. Unlike traditional chain-of-thought methods, SG-FSM tackles MHQA by iteratively breaking down complex questions into sub-questions, correcting itself to improve accuracy. It processes one sub-question at a time, dynamically deciding the next step based on the current context and results, functioning much like an automaton. Experiments across various benchmarks demonstrate the effectiveness of our approach, outperforming strong baselines on challenging datasets such as Musique. SG-FSM reduces hallucination, enabling recovery of the correct final answer despite intermediate errors. It also improves adherence to specified output formats, simplifying evaluation significantly.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
Wang, Xiaochen
He, Junqing
Chen, Liang
Yang, Reza Haf Zhe
Wang, Yiru
Meng, Xiangdi
Pan, Kunhao
Sui, Zhifang
Computation and Language
Large Language Models with chain-of-thought prompting, such as OpenAI-o1, have shown impressive capabilities in natural language inference tasks. However, Multi-hop Question Answering (MHQA) remains challenging for many existing models due to issues like hallucination, error propagation, and limited context length. To address these challenges and enhance LLMs' performance on MHQA, we propose the Self-Guiding prompting Finite State Machine (SG-FSM), designed to strengthen multi-hop reasoning abilities. Unlike traditional chain-of-thought methods, SG-FSM tackles MHQA by iteratively breaking down complex questions into sub-questions, correcting itself to improve accuracy. It processes one sub-question at a time, dynamically deciding the next step based on the current context and results, functioning much like an automaton. Experiments across various benchmarks demonstrate the effectiveness of our approach, outperforming strong baselines on challenging datasets such as Musique. SG-FSM reduces hallucination, enabling recovery of the correct final answer despite intermediate errors. It also improves adherence to specified output formats, simplifying evaluation significantly.
title SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine
topic Computation and Language
url https://arxiv.org/abs/2410.17021