arXiv AI
Sep 17
Probabilistic Linear Explanations
arXiv:2609. 19077v1 Announce Type: cross Abstract: Formal explainability provides mathematically grounded justifications for individual predictions.
The Query Channel: Information-Theoretic Limits of Masking-Based Explanations
arXiv:2604. 16689v2 Announce Type: replace Abstract: Masking-based post-hoc explanation methods, such as KernelSHAP and LIME, estimate local feature importance by querying a black-box model under randomized perturbations.
Related stories
arXiv AI
Aug 18
Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations
arXiv:2603. 14894v3 Announce Type: replace-cross Abstract: Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations.
arXiv AI
Jun 30
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.
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.
Hugging Face Trending Papers
Jun 22
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: language is a compressed and capacity-limited interface for conveying task information.
arXiv AI
Jun 30
Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data
arXiv:2606. 30372v1 Announce Type: new Abstract: Quantitative research across the social and behavioral sciences depends on human subject experiments that are expensive, slow, and subject to sampling bias.
arXiv AI
Jul 8
ExplAIner: A Declarative Query Language for Explaining Classification Models
arXiv:2607. 06407v1 Announce Type: new Abstract: The XAI community has studied a wide range of queries and scores for explaining predictions of ML models.
arXiv Machine Learning
Sep 21
On the Limits of Maximal Coding Rate Reduction for Out-of-Distribution Generalisation
The paper investigates the limits of the maximal coding rate reduction (MCR²) framework for out‑of‑distribution (OOD) generalisation. It shows that MCR² can lead to complete prediction failure under distribution shift, even when a perfectly stable feature is available, and that adding invariance principles from IRM or REx does not resolve this issue. The authors conclude that additional assumptions or learning principles are needed to guarantee stable OOD predictions with MCR².
arXiv Machine Learning
Jul 21
Rate-Distortion-Perception Theory: Redefining the Fundamental Limits of Information Representation
arXiv:2607. 17232v1 Announce Type: cross Abstract: Classical rate-distortion (RD) theory has long established the fundamental limits of lossy compression by quantifying the minimum number of bits required to represent a source under a prescribed distortion constraint.
arXiv Machine Learning
Jun 2
How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations
arXiv:2606. 02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control.
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.
arXiv AI
Jun 16
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
arXiv:2606. 14758v1 Announce Type: cross Abstract: As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial.