arXiv:2608. 06300v1 Announce Type: new Abstract: Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it critical to show that their scores depend on speaking proficiency rather than irrelevant speaker attributes such as first language (L1) or age.
arXiv:2609.18533v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representation...
Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representations. We ask whether speaker-linked attributes that...
The paper extends mechanistic interpretability of large language models by modeling concepts as low‑dimensional non‑linear manifolds rather than linear subspaces. It introduces a concept‑based alignment (CBA) score to compare these manifolds across layers and models, revealing block structures in intermediate layers, a shift from syntax‑dominated to mixed syntactic‑semantic concepts, and training‑dependent multilingual sharing. The study also shows that alignment patterns differ across model families and training stages, with adjacent stages aligning more closely than distant ones.
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:2608.29034v1 Announce Type: cross Abstract: A wide range of methods have been proposed for interpreting language models, delivering important insights into their inner workings. However, differ...
arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.
arXiv:2506. 20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure.
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
arXiv:2608. 06417v1 Announce Type: new Abstract: The proliferation of misinformation online has driven demand for scalable detection systems.
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.
arXiv:2608. 06908v1 Announce Type: cross Abstract: We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT).
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.