mlsanityData to 7 Oct 2026

Self-Reports Do Not Identify Self-Models: An Identifiability Test for Counterfactual Reports

arXiv 2609.32449 ↗First posted 26 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Language-model self-reports are evidence about behavior in a prompt environment, not by themselves evidence of a self-model. We investigate counterfactual reports about affect-like states under activation interventions and ask whether the report remains bound to the named intervention when the demonstration environment changes. Across three open instruction models, wrong-source demonstrations move reports toward the source answer family, while explicit mechanism binding reduces this pull. Self-report benchmarks should include environment-shift invariance tests under fixed intervention before treating accuracy as evidence for an autonomous report mechanism.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 26 Sep 2026.

Builds on

20 of 28 references.

References · 20

  1. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  2. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  4. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  5. 2023Steering Language Models With Activation Engineeringcited by 824
  6. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  7. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  8. 2021Causal Abstractions of Neural Networkscited by 401
  9. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 217
  10. 2023Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationscited by 197
  11. 2026Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnetcited by 175
  12. 2023Inspecting and Editing Knowledge Representations in Language Modelscited by 140
8 more
  1. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  2. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  3. 2017Learning Independent Causal Mechanismscited by 104
  4. 2026Emergent Introspective Awareness in Large Language Modelscited by 73
  5. 2022Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Datacited by 42
  6. 2025Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activationscited by 37
  7. 2025Training Language Models to Explain Their Own Computationscited by 27
  8. 2024Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learningcited by 16

Built on by

Not cited yet.