Layer-of-Thoughts Prompting (LoT): Leveraging LLM-Based Retrieval with Constraint Hierarchies

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fungwacharakorn, Wachara, Thanh, Nguyen Ha, Zin, May Myo, Satoh, Ken
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913548375949312
author Fungwacharakorn, Wachara
Thanh, Nguyen Ha
Zin, May Myo
Satoh, Ken
author_facet Fungwacharakorn, Wachara
Thanh, Nguyen Ha
Zin, May Myo
Satoh, Ken
contents This paper presents a novel approach termed Layer-of-Thoughts Prompting (LoT), which utilizes constraint hierarchies to filter and refine candidate responses to a given query. By integrating these constraints, our method enables a structured retrieval process that enhances explainability and automation. Existing methods have explored various prompting techniques but often present overly generalized frameworks without delving into the nuances of prompts in multi-turn interactions. Our work addresses this gap by focusing on the hierarchical relationships among prompts. We demonstrate that the efficacy of thought hierarchy plays a critical role in developing efficient and interpretable retrieval algorithms. Leveraging Large Language Models (LLMs), LoT significantly improves the accuracy and comprehensibility of information retrieval tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12153
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Layer-of-Thoughts Prompting (LoT): Leveraging LLM-Based Retrieval with Constraint Hierarchies
Fungwacharakorn, Wachara
Thanh, Nguyen Ha
Zin, May Myo
Satoh, Ken
Computation and Language
Artificial Intelligence
This paper presents a novel approach termed Layer-of-Thoughts Prompting (LoT), which utilizes constraint hierarchies to filter and refine candidate responses to a given query. By integrating these constraints, our method enables a structured retrieval process that enhances explainability and automation. Existing methods have explored various prompting techniques but often present overly generalized frameworks without delving into the nuances of prompts in multi-turn interactions. Our work addresses this gap by focusing on the hierarchical relationships among prompts. We demonstrate that the efficacy of thought hierarchy plays a critical role in developing efficient and interpretable retrieval algorithms. Leveraging Large Language Models (LLMs), LoT significantly improves the accuracy and comprehensibility of information retrieval tasks.
title Layer-of-Thoughts Prompting (LoT): Leveraging LLM-Based Retrieval with Constraint Hierarchies
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.12153