conftrace_

model interpretability

519 papers

Explore in graph

Co-occurring keywords

feature attribution (280) text classification (6793) neural network (6616) large language model (13587) explainable ai (480) model explanation (155) language model (4599) attention mechanism (4001) shapley value (206) representation learning (6206)

Papers

Do All Autoregressive Transformers Remember Facts the Same Way? A Cross-Architecture Analysis of Recall Mechanisms EMNLP 2025
Explaining Differences Between Model Pairs in Natural Language through Sample Learning EMNLP 2025
A Causal Lens for Evaluating Faithfulness Metrics EMNLP 2025
From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors EMNLP 2025
NormXLogit: The Head-on-Top Never Lies EMNLP 2025
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts? EMNLP 2025
Mixed Signals: Decoding VLMs’ Reasoning and Underlying Bias in Vision-Language Conflict EMNLP 2025
Do ImageNet-trained Models Learn Shortcuts? The Impact of Frequency Shortcuts on Generalization CVPR 2025
NOMATTERXAI: Generating “No Matter What” Alterfactual Examples for Explaining Black-Box Text Classification Models AAAI 2025
Transformer Layers as Painters AAAI 2025
LLM Attributor: Interactive Visual Attribution for LLM Generation AAAI 2025
TRANSFORMER EXPLAINER: Interactive Learning of Text-Generative Models AAAI 2025
Monitoring Primitive Interactions During the Training of DNNs AAAI 2025
Towards Trustable SHAP Scores AAAI 2025
Semi-supervised Concept Bottleneck Models ICCV 2025
Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networks IJCAI 2025
Interpretable Sparse Features for Probing Self-Supervised Speech Models IJCNLP 2025
Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models WACV 2025
A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models AAAI 2025
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? EMNLP 2025
Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property IJCAI 2025
o-MEGA: Optimized Methods for Explanation Generation and Analysis EMNLP 2025
Self-Critique and Refinement for Faithful Natural Language Explanations EMNLP 2025
How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders EMNLP 2025
TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models ICCV 2025