conftrace_
← Optimization & Theory
Deep Learning › Optimization & Theory ›

Interpretability

105 papers

Papers per year

7
6
8
13
8
12
20
17
14

Papers

Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026
TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors ACL 2026
A Layer-wise Analysis of Supervised Fine-Tuning ACL 2026
Tracing Logit Trajectories Across Layer Depth: Dataset-Level Explainability for Language Models ACL 2026
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures ACL 2026
Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures ACL 2026
Can LLM Safety Be Ensured by Constraining Parameter Regions? ACL 2026
Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning ACL 2026
Think Less, Code Better: Probing When Chain-of-Thought Hurts and How to Route Around It ACL 2026
Probing Functional Correctness in Diffusion Language Models ACL 2026
Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosis MIDL 2026
SoftCAM: Making black box models self-explainable for medical image analysis MIDL 2026
What Fine-Tuning Changes: A Radiomic Lens on Prostate Foundation Model Representations MIDL 2026
EFIQA: Explainable Fundus Image Quality Assessment via Anatomical Priors MIDL 2026
BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation AAAI 2025
Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks AAAI 2025
Position-aware Automatic Circuit Discovery ACL 2025
Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs ACL 2025
JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution ACL 2025
TokenShapley: Token Level Context Attribution with Shapley Value ACL 2025
Designing and Contextualising Probes for African Languages ACL 2025
Interpretable Image Classification via Non-parametric Part Prototype Learning CVPR 2025
LMO: Linear Mamba Operator for MRI Reconstruction CVPR 2025
Interpreting Object-level Foundation Models via Visual Precision Search CVPR 2025