Pith. sign in

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

arxiv 2501.15740 v1 pith:HEVFZ4KA submitted 2025-01-27 cs.AI

Propositional Interpretability in Artificial Intelligence

classification cs.AI
keywords propositionalinterpretabilityattitudesmethodscentralmechanismsprogramsome
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Impossibility of Eliciting Latent Knowledge

    cs.AI 2026-06 unverdicted novelty 7.0

    Proves that no behavior-dependent feedback training strategy can guarantee an honest agent for latent knowledge even with perfect training feedback.

  2. Radical AI Interpretability

    cs.AI 2026-06 unverdicted novelty 6.0

    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.

  3. A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents

    cs.LG 2026-02 conditional novelty 6.0

    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.

  4. The Impact of Off-Policy Training Data on Probe Generalisation

    cs.AI 2025-11 unverdicted novelty 6.0

    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...

  5. Do Linear Probes Generalize Better in Persona Coordinates?

    cs.AI 2026-05 unverdicted novelty 5.0

    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.

  6. Do Linear Probes Generalize Better in Persona Coordinates?

    cs.AI 2026-05 unverdicted novelty 5.0

    Probes on persona principal components from contrastive prompts generalize better than raw activation probes for harmful behaviors across 10 datasets.

  7. The New Associationism: Lessons from Deep Learning

    cs.AI 2026-05 unverdicted novelty 4.0

    Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.

  8. Mechanistic Interpretability Needs Philosophy

    cs.CL 2025-06 unverdicted novelty 4.0

    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.