arXiv subjects

Cristian Daniel Păduraru

Publications and source records attributed to Cristian Daniel Păduraru.

2 recordsLinked to original sources

arXiv2026

Bridging Explainability and Embeddings: BEE Aware of Spuriousness

Current methods for detecting spurious correlations rely on analyzing dataset statistics or error patterns, leaving many harmful shortcuts invisible when counterexamples are absent. We introduce BEE (Bridging Explainability and Embeddings), a framework that shifts the focus from model predictions to the weight space, and to the embedding geometry underlying decisions. By analyzing how fine-tuning perturbs pretrained representations, BEE uncovers spurious correlations that remain hidden from conventional evaluation pipelines. We use linear probing as a transparent diagnostic lens, revealing spurious features that not only persist after full fine-tuning but also transfer across diverse state-of-the-art models. Our experiments cover numerous datasets and domains: vision (Waterbirds, CelebA, ImageNet-1k), language (CivilComments, MIMIC-CXR medical notes), and multiple embedding families (CLIP, CLIP-DataComp.XL, mGTE, BLIP2, SigLIP2). BEE consistently exposes spurious correlations: from concepts that slash the ImageNet accuracy by up to 95%, to clinical shortcuts in MIMIC-CXR notes that induce dangerous false negatives. Together, these results position BEE as a general and principled tool for diagnosing spurious correlations in weight space, enabling principled dataset auditing and more trustworthy foundation models. The source code is publicly available at https://github.com/bit-ml/bee.

cs.AI↗

arXiv2025

Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure essentially rewrites the original activations as a weighted sum of decoder features. In contrast to existing literature, we forward an encoder-centric alternative to model steering which demonstrates a stronger cross-modal performance. We introduce S&P Top-K, a retraining-free and computationally lightweight Selection and Projection framework that identifies Top-K encoder features aligned with a sensitive attribute or behavior, optionally aggregates them into a single control axis, and computes an orthogonal projection to be subsequently applied directly in the model's native embedding space. In vision-language models, it improves fairness metrics on CelebA and FairFace by up to 3.2 times over conventional SAE usage, and in large language models, it substantially reduces aggressiveness and sycophancy in Llama-3 8B Instruct, achieving up to 3.6 times gains over masked reconstruction. These findings suggest that encoder-centric interventions provide a general, efficient, and more effective mechanism for shaping model behavior at inference time than the traditional decoder-centric use of SAEs.

cs.LG↗