Tag

#interpretability

12 articles tagged #interpretability

arxivJun 1bullish

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines

arXiv:2605.31183v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have been seen as a promising avenue for exploring the internals of Large Language Models (LLMs) and for steering model output generation. When AxBench - a model steering benchmark - was introduced in Wu et al. (2025), SAEs

SPLALO3 models #language-models #benchmark #interpretability Read on arxiv →

arxivMay 29

When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis

arXiv:2605.29025v1 Announce Type: new Abstract: Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes what policymakers see and which arguments register. Standard evaluation, anchored on stance accuracy a

#evaluation #interpretability #language-models Read on arxiv →

arxivMay 29

Evolving Features vs Evolving Entire Trees with GP for Interpretable Survival Analysis

arXiv:2605.30119v1 Announce Type: cross Abstract: Survival analysis concerns the task of predicting the time until an event occurs. Often used in the medical field, survival analysis deals with incomplete (i.e., censored) data, for instance, from patients who did not experience the event during the

#machine-learning #survival-analysis #evolutionary-computing Read on arxiv →

arxivMay 21bullish

INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification

arXiv:2605.20088v1 Announce Type: cross Abstract: Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of time-series classification (TSC) and to make model decision-making processes more transparent. However

IN1 model #time-series #classification #interpretability Read on arxiv →

arxivMay 15bullish

K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles

arXiv:2605.14828v1 Announce Type: cross Abstract: Existing clustering methods for functional data often prioritize partitioning accuracy over interpretability, making it challenging to extract meaningful insights when the data-generating process follows a specific underlying structure and an ordinal

K-1 model #clustering #interpretability #machine-learning Read on arxiv →

arxivMay 13bullish

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning

arXiv:2605.11467v1 Announce Type: new Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberative-looking steps that contribute nothing to correctness. This wastes inference tokens, pollutes interpretability

MEQWCL3 models #reasoning #reinforcement-learning #interpretability Read on arxiv →

arxivApr 29bullish

GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval

arXiv:2604.23779v1 Announce Type: cross Abstract: The semantic gap between colloquial user queries and professional legal documents presents a fundamental challenge in Legal Case Retrieval (LCR). Existing dense retrieval methods typically treat LCR as a black-box semantic matching process, neglectin

GLSAKE3 models #information retrieval #legal tech #generative models Read on arxiv →

arxivApr 27bullish

H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers

arXiv:2604.22045v1 Announce Type: cross Abstract: Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely on marginal effects, overlooking feature interactions, where groups o

VGREDE5 models · +2 #computer-vision #interpretability #image-classification Read on arxiv →

arxivApr 23

LayerTracer: A Joint Task-Particle and Vulnerable-Layer Analysis framework for Arbitrary Large Language Model Architectures

arXiv:2604.20556v1 Announce Type: cross Abstract: Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. However, the evolutionary laws of hierarchical representations, task knowledge formation positions, and

TRGAMA3 models #large-language-models #architecture #interpretability Read on arxiv →

arxivApr 18

Structural interpretability in SVMs with truncated orthogonal polynomial kernels

arXiv:2604.15285v1 Announce Type: cross Abstract: We study post-training interpretability for Support Vector Machines (SVMs) built from truncated orthogonal polynomial kernels. Since the associated reproducing kernel Hilbert space is finite-dimensional and admits an explicit tensor-product orthonorm

SU1 model #machine-learning #interpretability #kernel-methods Read on arxiv →

arxivApr 14

Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment

arXiv:2604.10673v1 Announce Type: new Abstract: AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when they are too

#alignment #interpretability #evaluation Read on arxiv →

arxivApr 9

Continuous Interpretive Steering for Scalar Diversity

arXiv:2604.07006v1 Announce Type: new Abstract: Pragmatic inference is inherently graded. Different lexical items give rise to pragmatic enrichment to different degrees. Scalar implicature exemplifies this property through scalar diversity, where implicature strength varies across scalar items. Howe

LA1 model #pragmatic-inference #language-models #interpretability Read on arxiv →

Tag