REVIEW 5 cited by
Specific versus General Principles for Constitutional AI
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Specific versus General Principles for Constitutional AI
read the original abstract
Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-preservation or power. Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles. We find this approach effectively prevents the expression of such behaviors. The success of simple principles motivates us to ask: can models learn general ethical behaviors from only a single written principle? To test this, we run experiments using a principle roughly stated as "do what's best for humanity". We find that the largest dialogue models can generalize from this short constitution, resulting in harmless assistants with no stated interest in specific motivations like power. A general principle may thus partially avoid the need for a long list of constitutions targeting potentially harmful behaviors. However, more detailed constitutions still improve fine-grained control over specific types of harms. This suggests both general and specific principles have value for steering AI safely.
Forward citations
Cited by 5 Pith papers
-
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
LLawCo extracts misaligned behavioral patterns from agent failures to derive laws, incorporates them via SFT into LLM reasoning, and reports 4.5% and 6.8% success rate gains on PARTNR-Dialog and TDW-MAT benchmarks.
-
Reinforcement Learning Towards Broadly and Persistently Beneficial Models
Reinforcement learning on beneficial traits in realistic domains yields broad improvements on over 80% of out-of-distribution alignment benchmarks and greater resistance to adversarial steering.
-
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
ATLAS shows constitutions induce recoverable latent geometry in LLMs that redistributes but remains detectable across models and neural perturbation data via source-defined families and AUC separations.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt...
-
Emergent alignment and the projectability of ethical personas
Narrow constitutional finetuning on safety sub-tasks induces emergent alignment across broader safety domains and yields projectable ethical personas whose signatures can be measured with a multidimensional diagnostic.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.