paper-with-me

Papers

Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition

2018-02-16 · Vikramjit Mitra, Horacio Franco

Unseen data can degrade performance of deep neural net acoustic models. To cope with unseen data, adaptation techniques are deployed. For unlabeled unseen data, one must generate some hypothesis given an existing model, which is used as the label for model adaptation. However, assessing the goodness of the hypothesis can be difficult, and an erroneous hypothesis can lead to poorly trained models. In such cases, a strategy to select data having reliable hypothesis can ensure better model adaptation. This work proposes a data-selection strategy for DNN model adaptation, where DNN output layer activations are used to ascertain the goodness of a generated hypothesis. In a DNN acoustic model, the output layer activations are used to generate target class probabilities. Under unseen data conditions, the difference between the most probable target and the next most probable target is decreased compared to the same for seen data, indicating that the model may be uncertain while generating its hypothesis. This work proposes a strategy to assess a model's performance by analyzing the output layer activations by using a distance measure between the most likely target and the next most likely target, which is used for data selection for performing unsupervised adaptation.

📄 PDF Abstract BibTeX arXiv:1802.06861

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation

2025-03-03 · Jonathan Jacobi, Gal Niv

Understanding and interpreting the internal representations of large language models (LLMs) remains an open challenge. Patchscopes introduced a method for probing internal activations by patching them into new prompts, p…

Language ModelingLanguage Modelling

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

2025-06-09 · Yifan Luo, Zhennan Zhou, Bin Dong arxiv

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong structural assumptions--such …

LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization

2025-10-05 · Jiarui Liu, Jivitesh Jain, Mona Diab, Nishant Subramani arxiv

Although large language models (LLMs) have tremendous utility, trustworthiness is still a chief concern: models often generate incorrect information with high confidence. While contextual information can help guide gener…

Interpreting Attention Layer Outputs with Sparse Autoencoders

2024-06-25 · Connor Kissane, Robert Krzyzanowski, Joseph Isaac Bloom, Arthur Conmy 외

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained trans…

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders

2025-05-12 · Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du 외

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically …