arXiv AI

Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors

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 Machine Learning

Jun 18

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

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.

By Dibyanayan Bandyopadhyay, Asif Ekbal

llms efficiency safety

arXiv AI

Jun 11

Cross-Layer Discrete Concept Discovery for Interpreting Language Models

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.

By Ankur Garg, Xuemin Yu, Hassan Sajjad, Samira Ebrahimi Kahou

llms diffusion efficiency

arXiv AI

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

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.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

arXiv Machine Learning

Aug 10

Latent Fact-Checking: Detecting Misinformation through Activation Engineering

arXiv:2608. 06417v1 Announce Type: new Abstract: The proliferation of misinformation online has driven demand for scalable detection systems.

By Pedro Barcelos, Ot\'avio Parraga, Marcelo M. Mussi, Lucas M. Fraga, Lucas S. Kupssinsk\"u, Rodrigo C. Barros

llms diffusion fine-tuning benchmarks safety

arXiv AI

Jul 21

Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence

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.

By Katarzyna Filus, Sebastian Pokuci\'nski

llms rag efficiency multimodal safety

arXiv AI

Aug 10

Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests

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).

By Seitaro Ono, Senna Ross, Jun Saiki

llms rag nlp benchmarks safety

arXiv Machine Learning

Aug 12

Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models

arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.

By Konstantinos P. Panousis, Diego Marcos

computer-vision efficiency multimodal safety

arXiv AI

Jun 6

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

arXiv:2606. 05173v1 Announce Type: cross Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure.

By Aimen Boukhari

rag diffusion benchmarks

arXiv AI

Jun 30

On the Faithfulness of Post-Hoc Concept Bottleneck Models

arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.

By Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler

llms multimodal benchmarks

arXiv AI

Jun 19

From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models

arXiv:2606. 20152v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have substantially transformed Automated Essay Scoring (AES), yet the internal mechanisms underlying LLM-based scoring remain poorly understood.

By Jiaxu Zuo, Mu You, Kaixin Lan, Tao Fang, Yujia Huo, Henghua Shen, Lidia S. Chao, Derek F. Wong

llms safety

arXiv AI

Jul 7

Unsupervised Features Mining via Activation Geometry

arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).

By Amit LeVi, Elad David, Max Fomin

llms safety

arXiv AI

Jun 26

Discovering Millions of Interpretable Features with Sparse Autoencoders

arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.

By XinYang He, Wei Wang, Bing Zhao, Xuan Ren, WenBo Li, WeiXu Qiao, Hu Wei, Lin Qu

llms efficiency

Related stories