mlsanityData to 7 Oct 2026

Unveiling LLM Mechanisms Through Neural ODEs and Control Theory

arXiv 2406.16985 ↗First posted 23 Jun 2024cs.LG cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes a framework combining Neural Ordinary Differential Equations (Neural ODEs) and robust control theory to enhance the interpretability and control of large language models (LLMs). By utilizing Neural ODEs to model the dynamic evolution of input-output relationships and introducing control mechanisms to optimize output quality, we demonstrate the effectiveness of this approach across multiple question-answer datasets. Experimental results show that the integration of Neural ODEs and control theory significantly improves output consistency and model interpretability, advancing the development of explainable AI technologies.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 23 Jun 2024.

Builds on

21 of 29 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  7. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,130
  8. 2016The Mythos of Model Interpretabilitycited by 716
  9. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 455
  10. 2019What do you learn from context? Probing for sentence structure in contextualized word representationscited by 436
  11. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  12. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
9 more
  1. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  2. 2023Function Vectors in Large Language Modelscited by 292
  3. 2019Latent ODEs for Irregularly-Sampled Time Seriescited by 182
  4. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
  5. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  6. 2024SelfIE: Self-Interpretation of Large Language Model Embeddingscited by 63
  7. 2023Sequential Integrated Gradients: a simple but effective method for explaining language modelscited by 52
  8. 2024Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultracited by 36
  9. 2024Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODEcited by 6

Built on by

Not cited yet.