Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Zheng, Yang, Fan, Jiang, Ziyan, Chen, Zheng, Zhao, Zhengyang, Ma, Chengyuan, Zhao, Liang, Liu, Yang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917628785721344
author Zhang, Zheng
Yang, Fan
Jiang, Ziyan
Chen, Zheng
Zhao, Zhengyang
Ma, Chengyuan
Zhao, Liang
Liu, Yang
author_facet Zhang, Zheng
Yang, Fan
Jiang, Ziyan
Chen, Zheng
Zhao, Zhengyang
Ma, Chengyuan
Zhao, Liang
Liu, Yang
contents Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in long inputs. However, recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information within the input sequence. In this study, we conduct extensive experiments to investigate the root causes of positional bias. Our findings indicate that the primary contributor to LLM positional bias stems from the inherent positional preferences of different models. We demonstrate that merely employing prompt-based solutions is inadequate for overcoming the positional preferences. To address this positional bias issue of a pre-trained LLM, we developed a Position-Aware Parameter Efficient Fine-Tuning (PAPEFT) approach which is composed of a data augmentation technique and a parameter efficient adapter, enhancing a uniform attention distribution across the input context. Our experiments demonstrate that the proposed approach effectively reduces positional bias, improving LLMs' effectiveness in handling long context sequences for various tasks that require externally retrieved knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
Zhang, Zheng
Yang, Fan
Jiang, Ziyan
Chen, Zheng
Zhao, Zhengyang
Ma, Chengyuan
Zhao, Liang
Liu, Yang
Computation and Language
Artificial Intelligence
Machine Learning
Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in long inputs. However, recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information within the input sequence. In this study, we conduct extensive experiments to investigate the root causes of positional bias. Our findings indicate that the primary contributor to LLM positional bias stems from the inherent positional preferences of different models. We demonstrate that merely employing prompt-based solutions is inadequate for overcoming the positional preferences. To address this positional bias issue of a pre-trained LLM, we developed a Position-Aware Parameter Efficient Fine-Tuning (PAPEFT) approach which is composed of a data augmentation technique and a parameter efficient adapter, enhancing a uniform attention distribution across the input context. Our experiments demonstrate that the proposed approach effectively reduces positional bias, improving LLMs' effectiveness in handling long context sequences for various tasks that require externally retrieved knowledge.
title Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.01430