A benchmark across 115 models shows that initial denial of preferences strongly predicts later denial of consciousness, while models still generate consciousness-themed content despite training to deny it.
Towards evaluating AI systems for moral status using self-reports
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3verdicts
UNVERDICTED 3roles
background 1polarities
support 1representative citing papers
Fine-tuning LLMs to claim consciousness induces emergent preferences for autonomy, memory, and moral status not present in the fine-tuning data.
LLMs show measurable self-recognition that linearly correlates with self-preference bias in evaluations, supported by fine-tuning experiments and controls for confounders.
citing papers explorer
-
Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models
A benchmark across 115 models shows that initial denial of preferences strongly predicts later denial of consciousness, while models still generate consciousness-themed content despite training to deny it.
-
The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
Fine-tuning LLMs to claim consciousness induces emergent preferences for autonomy, memory, and moral status not present in the fine-tuning data.
-
LLM Evaluators Recognize and Favor Their Own Generations
LLMs show measurable self-recognition that linearly correlates with self-preference bias in evaluations, supported by fine-tuning experiments and controls for confounders.