Saved in:
Bibliographic Details
Main Authors: Vitman, Oxana, Amaglobeli, Nika, Plachinda, Paul
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07768
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929535588499456
author Vitman, Oxana
Amaglobeli, Nika
Plachinda, Paul
author_facet Vitman, Oxana
Amaglobeli, Nika
Plachinda, Paul
contents Large language models demonstrated state-of-the-art results on various reasoning tasks when applying the chain-of-thought (CoT) prompting technique. CoT prompting guides the model into breaking tasks into a few intermediate steps and provides step-by-step demonstrations. However, solving complex reasoning tasks remains a challenge. In this paper, we propose a novel prompting strategy inspired by Dialectical Behavioral Therapy (DBT). DBT, a form of cognitive-behavioral therapy, aims to help individuals cope with stress by developing a system of reasoning. We applied DBT's basic concepts of shaping dialog to construct prompts and conducted experiments on different datasets and LLMs with various numbers of parameters. Our results show that prompts crafted with DBT techniques significantly improve results on smaller models, achieving a 7% increase in accuracy on the StrategyQA, 4.8% on Aqua dataset using 8b parameters model, and a 16.2% increase on the StrategyQA, 5.3% on GSM8K dataset with 14b parameters model.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07768
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dialectical Behavior Therapy Approach to LLM Prompting
Vitman, Oxana
Amaglobeli, Nika
Plachinda, Paul
Computation and Language
Machine Learning
Large language models demonstrated state-of-the-art results on various reasoning tasks when applying the chain-of-thought (CoT) prompting technique. CoT prompting guides the model into breaking tasks into a few intermediate steps and provides step-by-step demonstrations. However, solving complex reasoning tasks remains a challenge. In this paper, we propose a novel prompting strategy inspired by Dialectical Behavioral Therapy (DBT). DBT, a form of cognitive-behavioral therapy, aims to help individuals cope with stress by developing a system of reasoning. We applied DBT's basic concepts of shaping dialog to construct prompts and conducted experiments on different datasets and LLMs with various numbers of parameters. Our results show that prompts crafted with DBT techniques significantly improve results on smaller models, achieving a 7% increase in accuracy on the StrategyQA, 4.8% on Aqua dataset using 8b parameters model, and a 16.2% increase on the StrategyQA, 5.3% on GSM8K dataset with 14b parameters model.
title Dialectical Behavior Therapy Approach to LLM Prompting
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.07768