Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition
Ariel Goldstein, Gabriel Stanovsky
arXiv Preprint Archive March 1, 2024 via arXiv
Summary
AI-generated from the abstractLarge language models' capacity for understanding text is debated because opponents hold different definitions of understanding, particularly regarding the role of consciousness. A thought experiment involving an open-source chatbot that excels on all benchmarks yet lacks subjective experience shows that different schools of AI research answer the question of its understanding differently, revealing terminological disagreement. The paper proposes two working definitions for understanding that explicitly address consciousness, connecting to philosophy, psychology, and neuroscience literature.
Study at a glance
| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Keywords | Cs.cl |
| Key finding | Argues that debates over LLM understanding are rooted in conflicting definitions that differ on the role of consciousness, and proposes two working definitions to clarify the issue. |
Abstract
Recent advances in LLMs have sparked a debate on whether they understand text. In this position paper, we argue that opponents in this debate hold different definitions for understanding, and particularly differ in their view on the role of consciousness. To substantiate this claim, we propose a thought experiment involving an open-source chatbot $Z$ which excels on every possible benchmark, seemingly without subjective experience. We ask whether $Z$ is capable of understanding, and show that different schools of thought within seminal AI research seem to answer this question differently, uncovering their terminological disagreement. Moving forward, we propose two distinct working definitions for understanding which explicitly acknowledge the question of consciousness, and draw connections with a rich literature in philosophy, psychology and neuroscience.