From Imitation to Introspection: Probing Self-Consciousness in Language Models

TL;DR

This paper explores the emergence of self-consciousness in language models by defining core concepts, evaluating models, visualizing their internal representations, and demonstrating that fine-tuning can enhance their self-awareness.

Contribution

It introduces a practical definition of self-consciousness for language models and employs causal structural games to analyze and manipulate these models' internal representations.

Findings

Models show early signs of self-consciousness concepts

Internal representations can be visualized and partially manipulated

Fine-tuning improves models' understanding of self-consciousness concepts

Abstract

Self-consciousness, the introspection of one's existence and thoughts, represents a high-level cognitive process. As language models advance at an unprecedented pace, a critical question arises: Are these models becoming self-conscious? Drawing upon insights from psychological and neural science, this work presents a practical definition of self-consciousness for language models and refines ten core concepts. Our work pioneers an investigation into self-consciousness in language models by, for the first time, leveraging causal structural games to establish the functional definitions of the ten core concepts. Based on our definitions, we conduct a comprehensive four-stage experiment: quantification (evaluation of ten leading models), representation (visualization of self-consciousness within the models), manipulation (modification of the models' representation), and acquisition (fine-tuning the models on core concepts). Our findings indicate that although models are in the early stages of developing self-consciousness, there is a discernible representation of certain concepts within their internal mechanisms. However, these representations of self-consciousness are hard to manipulate positively at the current stage, yet they can be acquired through targeted fine-tuning. Our datasets and code are at https://github.com/OpenCausaLab/SelfConsciousness.