mlsanityData to 14 Oct 2026

Flexible Model Interpretability through Natural Language Model Editing

arXiv 2311.10905 ↗First posted 17 Nov 2023cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Model interpretability and model editing are crucial goals in the age of large language models. Interestingly, there exists a link between these two goals: if a method is able to systematically edit model behavior with regard to a human concept of interest, this editor method can help make internal representations more interpretable by pointing towards relevant representations and systematically manipulating them.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 13 references that are in the map. First posted on arXiv 17 Nov 2023.

Builds on

9 of 13 references.

References · 9

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  3. 2022In-context Learning and Induction Headscited by 964
  4. 2022Memory-Based Model Editing at Scalecited by 447
  5. 2021Causal Abstractions of Neural Networkscited by 422
  6. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 110
  7. 2023Interpretability at Scale: Identifying Causal Mechanisms in Alpacacited by 103
  8. 2022CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behaviorcited by 55
  9. 2021Sparse Interventions in Language Models with Differentiable Maskingcited by 34

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Unifying Interpretability and Control: Evaluation via Intervention
  2. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
  3. 2025Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
  4. 2026Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
  5. 2023DUnE: Dataset for Unified Editing
  6. 2024Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
  7. 2026Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
  8. 2024The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse