REVIEW 8 cited by
Propositional Interpretability in Artificial Intelligence
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
Propositional Interpretability in Artificial Intelligence
read the original abstract
Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to date. I argue for the importance of propositional interpretability, which involves interpreting a system's mechanisms and behavior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probability) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems that log all of the relevant propositional attitudes in an AI system over time. I examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including those grounded in psychosemantics) to assess their strengths and weaknesses as methods of propositional interpretability.
Forward citations
Cited by 8 Pith papers
-
The Impossibility of Eliciting Latent Knowledge
Proves that no behavior-dependent feedback training strategy can guarantee an honest agent for latent knowledge even with perfect training feedback.
-
Radical AI Interpretability
A framework is proposed for solving for an AI system's beliefs and desires from its computational facts, with criteria for success tied to interpretability tests and emphasis on holistic attribution.
-
A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
An LLM navigation agent encodes a coarse spatial map and multi-step plans in its activations, and reasoning shifts these representations from broad environment information to immediate action selection.
-
The Impact of Off-Policy Training Data on Probe Generalisation
Off-policy training data for LLM behavior probes causes significant generalization failures especially for intent-based behaviors like deception, and performance on coerced incentivised data correlates with real on-po...
-
Do Linear Probes Generalize Better in Persona Coordinates?
Persona axes derived from contrastive prompts and PCA yield linear probes that generalize better than raw-activation probes across 10 datasets for deception and sycophancy.
-
Do Linear Probes Generalize Better in Persona Coordinates?
Probes on persona principal components from contrastive prompts generalize better than raw activation probes for harmful behaviors across 10 datasets.
-
The New Associationism: Lessons from Deep Learning
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
-
Mechanistic Interpretability Needs Philosophy
The paper claims that mechanistic interpretability needs philosophy as a partner to clarify concepts, refine methods, and navigate epistemic and ethical complexities in AI systems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.