paper-with-me

홈 › Papers

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

2025-09-10 · Yujian Ma, Xikun Lu, Jinqiu Sang, Xianquan Jiang, Ruizhe Li 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-tuning method, yet its underlying mechanisms in speech tasks remain poorly understood. In this work, we conduct the first systematic mechanistic interpretability study of LoRA within the Whisper encoder for speech emotion recognition (SER). Using a suite of analytical tools, including layer contribution probing, logit-lens inspection, and representational similarity via singular value decomposition (SVD) and centered kernel alignment (CKA), we reveal two key mechanisms: a delayed specialization process that preserves general features in early layers before consolidating task-specific information, and a forward alignment, backward differentiation dynamic between LoRA's matrices. Our findings clarify how LoRA reshapes encoder hierarchies, providing both empirical insights and a deeper mechanistic understanding for designing efficient and interpretable adaptation strategies in large speech models. Our code is available at https://github.com/harryporry77/Behind-the-Scenes.

📄 PDF Abstract BibTeX arXiv:2509.08454

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningSpeech Emotion Recognition

Similar Papers 제목 키워드 기반

DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction

2024-09-16 · John Wu, David Wu, Jimeng Sun

Predicting high-dimensional or extreme multilabels, such as in medical coding, requires both accuracy and interpretability. Existing works often rely on local interpretability methods, failing to provide comprehensive ex…

Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering

2024-11-17 · Zeping Yu, Sophia Ananiadou

Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies. While recent studies have yielded valuable insights into the mechanisms of textual LLMs, the mecha…

HallucinationIn-Context LearningQuestion AnsweringVisual Question Answering+1

A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i

2025-05-01 · Kola Ayonrinde, Louis Jaburi

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understand…

Philosophy

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…

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…