conftrace_

model analysis

56 papers

Explore in graph

Co-occurring keywords

model interpretability (519) language model (4599) large language model (13587) representation learning (6206) neural network (6616) neural network interpretability (114) feature attribution (280) linguistic knowledge (77) pretrained language model (1030) attention mechanism (4001)

Papers

Calibration Across Layers: Understanding Calibration Evolution in LLMs EMNLP 2025
Circuit-Tracer: A New Library for Finding Feature Circuits EMNLP 2025
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads EMNLP 2025
A Graph-Theoretical Framework for Analyzing the Behavior of Causal Language Models EMNLP 2025
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models ACL 2025
Math Neurosurgery: Isolating Language Models’ Math Reasoning Abilities Using Only Forward Passes ACL 2025
Fingerprinting LLMs through Survey Item Factor Correlation: A Case Study on Humor Style Questionnaire EMNLP 2025
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety EMNLP 2025
Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing EMNLP 2025
Explainability and Interpretability of Multilingual Large Language Models: A Survey EMNLP 2025
TRACE: Training and Inference-Time Interpretability Analysis for Language Models EMNLP 2025
From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens EMNLP 2025
Causal Estimation of Memorisation Profiles ACL 2024
Properties and Challenges of LLM-Generated Explanations NAACL 2024
Transformer Doctor: Diagnosing and Treating Vision Transformers NIPS 2024
Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods CVPR 2024
Measuring Per-Unit Interpretability at Scale Without Humans NIPS 2024
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 EMNLP 2024
Local Interpretation of Transformer Based on Linear Decomposition ACL 2023
Emergent Modularity in Pre-trained Transformers ACL 2023
Towards Extracting and Understanding the Implicit Rubrics of Transformer Based Automatic Essay Scoring Models ACL 2023
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling ICML 2023
A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models EMNLP 2023
Inseq: An Interpretability Toolkit for Sequence Generation Models ACL 2023