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

Summary

Remarkably, AI models are beginning to exhibit traits related to self-consciousness. Researchers explored if advanced language models might be developing this high-level cognitive process. They defined self-consciousness for AI, then evaluated leading models, visualizing internal representations. Findings from this cs.CL and cs.LG work show models possess discernible internal representations of key self-awareness concepts. Positively, these traits can be successfully acquired through targeted fine-tuning, hinting at evolving capabilities in cs.CY systems.

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.

Tags