Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines

TL;DR

This paper introduces LongGuide, a method that improves long-form generation in large language models by explicitly guiding task language and format, surpassing traditional in-context learning methods.

Contribution

It proposes a novel guideline-based approach to explicitly teach task distributions, significantly enhancing LLM performance in long-form tasks.

Findings

LongGuide improves LLM performance by over 5% in zero- and few-shot settings.

Guidelines effectively teach task language and format for better generation.

Method generalizes across models and integrates with prompt optimization.

Abstract

In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples, termed demonstrations, without fine-tuning. Although effective in question answering, ICL often underperforms in long-form generation tasks such as summarization. Under appropriately realistic assumptions, we empirically and theoretically show that ICL demonstrations alone are insufficient to teach LLMs the task language and format distributions for generation. We argue for explicit exposure to the task distributions and hypothesize that defining them by prompting enhances model performance. To this end, we present LongGuide, which efficiently generates two parallel streams of guidelines capturing task language and format properties: (i) Metric Guidelines (MGs) that instruct models to optimize self-evaluated metrics; and (ii) Output Constraint Guidelines (OCGs) that constrain generation at both token and sentence levels. LongGuide automatically selects the best combination of guidelines, improving both strong open- and closed-source LLMs by over 5% in both zero- and few-shot settings. We show that LongGuide is generalizable, learnable by weak models to enhance strong ones, and integrates synergistically with automatic prompt optimizers.