arXiv Computation and Language
On the Interpretability of Whisper Encodings Using Sparse Autoencoders
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jun 10
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders
arXiv:2606. 10029v1 Announce Type: cross Abstract: Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream.
Hugging Face Trending Papers
Aug 13
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.
arXiv AI
Jun 8
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
arXiv:2606. 07473v1 Announce Type: cross Abstract: Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input.
arXiv Computation and Language
Sep 4
Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe
The paper introduces an Encoding Probe that reconstructs language model representations using interpretable features, addressing limitations of traditional decoding probes such as incomparable feature contributions and correlation effects. It evaluates this approach on text and speech transformer models, examining features from acoustics, phonetics, syntax, lexicon, and speaker identity. Findings reveal that speaker-related effects vary with training objectives and datasets, while syntactic and lexical features independently contribute to reconstruction, offering a complementary perspective on model interpretation.
arXiv AI
Jun 15
Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models
arXiv:2606. 14647v1 Announce Type: cross Abstract: Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret.
arXiv Machine Learning
Sep 10
WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers
arXiv:2509.10452v3 Announce Type: replace-cross Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance....