Mixture of In-Context Experts Enhance LLMs' Long Context Awareness

TL;DR

This paper introduces MoICE, a novel method that enhances large language models' long context awareness by dynamically routing attention to specific positional information, improving performance without significant efficiency loss.

Contribution

MoICE is a new approach that uses position-specific experts and lightweight training to improve LLMs' long context understanding and generation capabilities.

Findings

MoICE outperforms previous methods on long context tasks.

It maintains high inference efficiency.

Effective for models like Llama and Mistral.

Abstract

Many studies have revealed that large language models (LLMs) exhibit uneven awareness of different contextual positions. Their limited context awareness can lead to overlooking critical information and subsequent task failures. While several approaches have been proposed to enhance LLMs' context awareness, achieving both effectiveness and efficiency remains challenging. In this paper, for LLMs utilizing RoPE as position embeddings, we introduce a novel method called "Mixture of In-Context Experts" (MoICE) to address this challenge. MoICE comprises two key components: a router integrated into each attention head within LLMs and a lightweight router-only training optimization strategy: (1) MoICE views each RoPE angle as an `in-context' expert, demonstrated to be capable of directing the attention of a head to specific contextual positions. Consequently, each attention head flexibly processes tokens using multiple RoPE angles dynamically selected by the router to attend to the needed positions. This approach mitigates the risk of overlooking essential contextual information. (2) The router-only training strategy entails freezing LLM parameters and exclusively updating routers for only a few steps. When applied to open-source LLMs including Llama and Mistral, MoICE surpasses prior methods across multiple tasks on long context understanding and generation, all while maintaining commendable inference efficiency.