mlsanityData to 14 Oct 2026

Mechanistic Interpretability of Socio-Political Frames in Language Models

arXiv 2510.03799 ↗First posted 4 Oct 2025cs.CL cs.AI cs.CYcited by 0

On the map: Mechanistic interpretability → Probing deception, bias and beliefs

Abstract (arXiv)

This paper explores the ability of large language models to generate and recognize deep cognitive frames, particularly in socio-political contexts. We demonstrate that LLMs are highly fluent in generating texts that evoke specific frames and can recognize these frames in zero-shot settings. Inspired by mechanistic interpretability research, we investigate the location of the `strict father' and `nurturing parent' frames within the model's hidden representation, identifying singular dimensions that correlate strongly with their presence. Our findings contribute to understanding how LLMs capture and express meaningful human concepts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability. Builds on 12 of its 29 references that are in the map. First posted on arXiv 4 Oct 2025.

Builds on

12 of 29 references.

References · 12

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  5. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  6. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  7. 2024Yi: Open Foundation Models by 01.AIcited by 719
  8. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 532
  9. 2023Language Models Represent Space and Timecited by 316
  10. 2021A Systematic Investigation of Commonsense Knowledge in Large Language Modelscited by 56
  11. 2022Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languagescited by 30
  12. 2023FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learningcited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Mechanistic Indicators of Understanding in Large Language Models
  2. 2024Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation
  3. 2025Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
  4. 2026Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
  5. 2025Linear Representations of Political Perspective Emerge in Large Language Models
  6. 2025GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models
  7. 2025When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth
  8. 2024Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks