paper-with-me

홈 › Papers

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications

2025-07-14 · Yoon Pyo Lee arxiv

The integration of Large Language Models (LLMs) into safety-critical domains, such as nuclear engineering, necessitates a deep understanding of their internal reasoning processes. This paper presents a novel methodology for interpreting how an LLM encodes and utilizes domain-specific knowledge, using a Boiling Water Reactor system as a case study. We adapted a general-purpose LLM (Gemma-3-1b-it) to the nuclear domain using a parameter-efficient fine-tuning technique known as Low-Rank Adaptation. By comparing the neuron activation patterns of the base model to those of the fine-tuned model, we identified a sparse set of neurons whose behavior was significantly altered during the adaptation process. To probe the causal role of these specialized neurons, we employed a neuron silencing technique. Our results demonstrate that while silencing most of these specialized neurons individually did not produce a statistically significant effect, deactivating the entire group collectively led to a statistically significant degradation in task performance. Qualitative analysis further revealed that silencing these neurons impaired the model's ability to generate detailed, contextually accurate technical information. This paper provides a concrete methodology for enhancing the transparency of an opaque black-box model, allowing domain expertise to be traced to verifiable neural circuits. This offers a pathway towards achieving nuclear-grade artificial intelligence (AI) assurance, addressing the verification and validation challenges mandated by nuclear regulatory frameworks (e.g., 10 CFR 50 Appendix B), which have limited AI deployment in safety-critical nuclear operations.

📄 PDF Abstract BibTeX arXiv:2507.09931

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

Behind the Scenes: Mechanistic Interpretability of LoRA-adapted Whisper for Speech Emotion Recognition

2025-09-10 · Yujian Ma, Xikun Lu, Jinqiu Sang, Xianquan Jiang 외 arxiv

Large pre-trained speech models such as Whisper offer strong generalization but pose significant challenges for resource-efficient adaptation. Low-Rank Adaptation (LoRA) has become a popular parameter-efficient fine-tuni…

parameter-efficient fine-tuningSpeech Emotion Recognition

From Neurons to Neutrons: A Case Study in Interpretability

2024-05-27 · Ouail Kitouni, Niklas Nolte, Víctor Samuel Pérez-Díaz, Sokratis Trifinopoulos 외

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a…

Insights into a radiology-specialised multimodal large language model with sparse autoencoders

2025-07-17 · Kenza Bouzid, Shruthi Bannur, Felix Meissen, Daniel Coelho de Castro 외 arxiv

Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic interpretability, p…

Domain-adapted large language models for classifying nuclear medicine reports

2023-03-01 · Zachary Huemann, Changhee Lee, Junjie Hu, Steve Y. Cho 외

With the growing use of transformer-based language models in medicine, it is unclear how well these models generalize to nuclear medicine which has domain-specific vocabulary and unique reporting styles. In this study, w…

Domain AdaptationLanguage ModelingLanguage ModellingMasked Language Modeling

Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations

2026-02-13 · Ajay Pravin Mahale arxiv

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges…