Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment
Abstract: Recent studies have explored the working mechanisms of In-Context Learning (ICL). However, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice.
To address this gap, we investigate the impact of demonstrations on token representations within the practical alignment tasks. We find that the transformer embeds the task function learned from demonstrations into the separator token representation, which plays an important role in the generation of prior response tokens. Once the prior response tokens are determined, the demonstrations become redundant.
Motivated by this finding, we propose an efficient Progressive In-Context Alignment (PICA) method consisting of two stages. In the first few-shot stage, the model generates several prior response tokens via standard ICL while concurrently extracting the ICL vector that stores the task function from the separator token representation. In the following zero-shot stage, this ICL vector guides the model to generate responses without further demonstrations.
Extensive experiments demonstrate that our PICA not only surpasses vanilla ICL but also achieves comparable performance to other alignment tuning methods. The proposed training-free method reduces the time cost (e.g., 5.45×) with improved alignment performance (e.g., 6.57+).
Consequently, our work highlights the application of ICL for alignment and calls for a deeper understanding of ICL for complex generations.
Paper Type: Long
Research Area: NLP Applications
Research Area Keywords: In-context Learning,Alignment,Large Language Model
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency
Languages Studied: English
Submission Number: 4767
Loading