How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond

TL;DR

This survey reviews the principles, formalizations, and challenges of human-model cooperation in NLP, highlighting recent progress and proposing a unified taxonomy to guide future research in this emerging field.

Contribution

It introduces a comprehensive taxonomy of human-model cooperation approaches and discusses open challenges, serving as a foundational overview for future advancements.

Findings

Unified taxonomy of human-model cooperation approaches

Identification of open challenges and frontier areas

Framework for future research directions in NLP cooperation

Abstract

With the advancement of large language models (LLMs), intelligent models have evolved from mere tools to autonomous agents with their own goals and strategies for cooperating with humans. This evolution has birthed a novel paradigm in NLP, i.e., human-model cooperation, that has yielded remarkable progress in numerous NLP tasks in recent years. In this paper, we take the first step to present a thorough review of human-model cooperation, exploring its principles, formalizations, and open challenges. In particular, we introduce a new taxonomy that provides a unified perspective to summarize existing approaches. Also, we discuss potential frontier areas and their corresponding challenges. We regard our work as an entry point, paving the way for more breakthrough research in this regard.