Skip to content

EMNLP 2024 Findings: How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment

Notifications You must be signed in to change notification settings

li-aolong/how-far-can-ica-go

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment

EMNLP 2024 Findings: How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment

Introduction

Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as In-Context Alignment (ICA), indicating that models can comprehend human instructions without requiring parameter adjustments. However, the exploration of the mechanism and applicability of ICA remains limited. In this paper, we begin by dividing the context text used in ICA into three categories: format, system prompt, and example. Through ablation experiments, we investigate the effectiveness of each part in enabling ICA to function effectively. We then examine how variants in these parts impact the model's alignment performance. Our findings indicate that the example part is crucial for enhancing the model's alignment capabilities, with changes in examples significantly affecting alignment performance. We also conduct a comprehensive evaluation of ICA's zero-shot capabilities in various alignment tasks. The results indicate that compared to parameter fine-tuning methods, ICA demonstrates superior performance in knowledge-based tasks and tool-use tasks. However, it still exhibits certain limitations in areas such as multi-turn dialogues and instruction following.


Codes are being organized.

About

EMNLP 2024 Findings: How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published