Zakharova, Daria (2025) Missing the Subject: Introspection in Large Language Models. [Preprint]

	Text Introspection in LLMs.pdf - Submitted Version Download (408kB)
	Text Introspection in LLMs_DZ.docx Download (90kB)

Abstract

Recent philosophical work has proposed a “lightweight account” of introspection, on which a system introspects when it represents its own mental states in a way that makes these states accessible for guiding behavior. This approach has informed empirical proposals for detecting introspective abilities in current LLMs. I argue that this lightweight account is too permissive and fails to capture what is essential to genuine introspection. This paper proceeds through three increasingly concessive but individually sufficient challenges to the attribution of introspective abilities to LLMs. First, LLMs lack the persistent subject necessary for genuine introspection, as current models lack the psychological continuity relationship needed for self knowledge. Second, LLM self-reports violate the immunity to error through misidentification that characterizes genuine introspection, because they are based on public textual information that could equally support judgments about another system’s states. Third, by centering on functional self-monitoring and behavioral control, the lightweight account fails to distinguish introspection from ubiquitous self-regulatory processes in complex systems.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Zakharova, Daria d.zakharova1@lse.ac.uk
Keywords:	Large Language Models; LLMs; Consciousness; Introspection; AI; Cognition; Immunity to error through misidentification; Persisting Subject
Subjects:	Specific Sciences > Artificial Intelligence > AI and Ethics Specific Sciences > Artificial Intelligence > Classical AI Specific Sciences > Artificial Intelligence General Issues > History of Philosophy of Science Specific Sciences > Artificial Intelligence > Machine Learning Specific Sciences > Psychology General Issues > Technology
Depositing User:	Daria Zakharova
Date Deposited:	05 Dec 2025 13:46
Last Modified:	05 Dec 2025 13:46
Item ID:	27377
Subjects:	Specific Sciences > Artificial Intelligence > AI and Ethics Specific Sciences > Artificial Intelligence > Classical AI Specific Sciences > Artificial Intelligence General Issues > History of Philosophy of Science Specific Sciences > Artificial Intelligence > Machine Learning Specific Sciences > Psychology General Issues > Technology
Date:	29 October 2025
URI:	https://philsci-archive.pitt.edu/id/eprint/27377

Available Versions of this Item

• Missing the Subject: Introspection in Large Language Models. (deposited 30 Oct 2025 13:00)
  • Missing the Subject: Introspection in Large Language Models. (deposited 05 Dec 2025 13:46)
    • Missing the Subject: Introspection in Large Language Models. (deposited 05 Dec 2025 13:46) [Currently Displayed]

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item