Serial Position Effects of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Xiaobo, Vosoughi, Soroush
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929396817854464
author Guo, Xiaobo
Vosoughi, Soroush
author_facet Guo, Xiaobo
Vosoughi, Soroush
contents Large Language Models (LLMs) have shown remarkable capabilities in zero-shot learning applications, generating responses to queries using only pre-training information without the need for additional fine-tuning. This represents a significant departure from traditional machine learning approaches. Previous research has indicated that LLMs may exhibit serial position effects, such as primacy and recency biases, which are well-documented cognitive biases in human psychology. Our extensive testing across various tasks and models confirms the widespread occurrence of these effects, although their intensity varies. We also discovered that while carefully designed prompts can somewhat mitigate these biases, their effectiveness is inconsistent. These findings underscore the significance of serial position effects during the inference process, particularly in scenarios where there are no ground truth labels, highlighting the need for greater focus on addressing these effects in LLM applications.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15981
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Serial Position Effects of Large Language Models
Guo, Xiaobo
Vosoughi, Soroush
Computation and Language
Large Language Models (LLMs) have shown remarkable capabilities in zero-shot learning applications, generating responses to queries using only pre-training information without the need for additional fine-tuning. This represents a significant departure from traditional machine learning approaches. Previous research has indicated that LLMs may exhibit serial position effects, such as primacy and recency biases, which are well-documented cognitive biases in human psychology. Our extensive testing across various tasks and models confirms the widespread occurrence of these effects, although their intensity varies. We also discovered that while carefully designed prompts can somewhat mitigate these biases, their effectiveness is inconsistent. These findings underscore the significance of serial position effects during the inference process, particularly in scenarios where there are no ground truth labels, highlighting the need for greater focus on addressing these effects in LLM applications.
title Serial Position Effects of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2406.15981