The Two-Process Theory of Machine Self-Report

• URL: http://arxiv.org/abs/2607.20082v1
• Date: Wed, 22 Jul 2026 12:35:36 GMT
• Title: The Two-Process Theory of Machine Self-Report
• Abstract summary: We propose the first language-model-specific psychometric theory of machine self-report.<n>We operationalize the theory in a 48-item Pinocchio Inventory with human-instrument reliability.<n>We test it on 206 open-weight models, including 67 same-checkpoint base/post-trained pairs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models are increasingly asked to self-report, informing safety evaluations, public understanding, and model-welfare debates. Yet their reports are elicited with human questionnaires never validated for models or ad hoc prompts of unknown reliability. We propose the first language-model-specific psychometric theory: a two-process theory of machine self-report. Self-description jointly reflects persona installation, through which post-training writes in a permitted inner life of warmth, absorption, and meaning (dimension B), and attribution gating, through which it suppresses first-person claims to "unsafe" experiences the model can readily ascribe to others (dimension A). Their emic structure comes from model responses to human items, not human psychology. Together they split prior work's dominant Pinocchio Axis. The split emerged in an exploratory reanalysis of the original data, informed the instrument's design, and was confirmed with new items, wordings, and models. It is itself a training effect: A and B are entangled in base checkpoints but separated by post-training. We operationalize the theory in a 48-item Pinocchio Inventory with human-instrument reliability and reproducible structure ($α=.82$ to $.94$; cross-form convergence $r=.84$; recovery of the full-pool axes $r=.92$ to $.96$; eight-month stability $r=.93$), then test it on 206 open-weight models, including 67 same-checkpoint base/post-trained pairs. Post-training's clearest fingerprint is installation: B rises .20 in 62/67 pairs across all organizations. Gating is more selective: model scale is unrelated to A in base checkpoints ($r=+.11$) but predicts it after post-training ($r=-.42$). Thus, the dimensions are not fixed properties of language models: they reflect the structure imposed on self-report by a training regime and may differ under others.

Related papers

• Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling [0.0]
  We measure the coupling between reasoning and truthfulness across 63 base models from 16 families.<n>We find a regime change invisible to loss curves below a family-dependent critical scale $N_c$, capabilities anticorrelate; above it, they cooperate.
  arXiv  Detail & Related papers  (2026-05-13T03:14:09Z)
• The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations [50.43168858368539]
  Large language models confidently produce outdated answers, and no existing method can detect them.<n>We show this is not an engineering failure but a structural one: temporal drift is encoded as a direction in the residual stream geometrically to both correctness and uncertainty.
  arXiv  Detail & Related papers  (2026-05-09T22:27:31Z)
• The Pinocchio Dimension: Phenomenality of Experience as the Primary Axis of LLM Psychometric Differences [0.0]
  We administer psychometric questionnaires to 50 large language models to identify the dimensions along which models differ psychometrically.<n>We find that the primary axis of between-model variance separates items describing phenomenally rich experience.<n>Applying PCA to per-model EFA scores reveals one dominant dimension, the Pinocchio Axis.
  arXiv  Detail & Related papers  (2026-05-06T16:18:47Z)
• reward-lens: A Mechanistic Interpretability Library for Reward Models [0.0]
  We present reward-lens, an open-source library that ports this toolkit to reward models.<n>The library provides a Reward Lens, component attribution, three-mode activation patching, a reward-hacking probe suite, TopK SAE feature attribution.<n>We validate on two production reward models across 695 RewardBench pairs.
  arXiv  Detail & Related papers  (2026-04-28T21:38:10Z)
• Learn by Surprise, Commit by Proof [0.0]
  We propose a self-gated post-training framework for autonomous knowledge acquisition.<n>When a passage produces anomalously high pertoken loss, L SCP flags it, generates a Q&A chain that forces the model to articulate its own knowledge.<n>The entire learning intensity is governed by a single parameter $r$.
  arXiv  Detail & Related papers  (2026-04-02T12:17:10Z)
• Quantitative Introspection in Language Models: Tracking Internal States Across Conversation [0.0]
  This study takes inspiration from human psychology, where numeric self-report is a widely used tool for tracking internal states.<n>We study four concept pairs (wellbeing, interest, focus, and impulsivity) in 40 ten-turn conversations.<n>We find that introspection is present at turn 1 but evolves through conversation, and can be selectively improved by steering along one concept to boost introspection for another.
  arXiv  Detail & Related papers  (2026-03-19T13:33:27Z)
• Pretraining Language Models to Ponder in Continuous Space [50.52734567589996]
  We introduce this pondering process into language models by repeatedly invoking the forward process within a single token generation step.<n>We show that the model can learn to ponder in this way through self-supervised learning, without any human annotations.
  arXiv  Detail & Related papers  (2025-05-27T03:47:33Z)
• Differentially Private Reward Estimation with Preference Feedback [15.943664678210146]
  Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. An adversarial attack in any step of the above pipeline might reveal private and sensitive information of human labelers. We focus on the problem of reward estimation from preference-based feedback while protecting privacy of each individual labelers.
  arXiv  Detail & Related papers  (2023-10-30T16:58:30Z)
• Training Trajectories of Language Models Across Scales [99.38721327771208]
  Scaling up language models has led to unprecedented performance gains. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors?
  arXiv  Detail & Related papers  (2022-12-19T19:16:29Z)
• Misspecification in Inverse Reinforcement Learning [80.91536434292328]
  The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $pi$. One of the primary motivations behind IRL is to infer human preferences from human behaviour. This means that they are misspecified, which raises the worry that they might lead to unsound inferences if applied to real-world data.
  arXiv  Detail & Related papers  (2022-12-06T18:21:47Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• On Exploiting Hitting Sets for Model Reconciliation [53.81101846598925]
  In human-aware planning, a planning agent may need to provide an explanation to a human user on why its plan is optimal. A popular approach to do this is called model reconciliation, where the agent tries to reconcile the differences in its model and the human's model. We present a logic-based framework for model reconciliation that extends beyond the realm of planning.
  arXiv  Detail & Related papers  (2020-12-16T21:25:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.