conftrace_

interpretability evaluation

8 papers

Explore in graph

Co-occurring keywords

latent representation (418) language model (4599) sparse autoencoder (112) large language model (13587) feature alignment (416) latent semantic space (3) unsupervised text analysis (1) held-out likelihood (1) semantic meaning (12) unsupervised analysis (1)

Papers

SFAL: Semantic-Functional Alignment Scores for Distributional Evaluation of Auto-Interpretability in Sparse Autoencoders EMNLP 2025
FADE: Why Bad Descriptions Happen to Good Features ACL 2025
Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling ACL 2023
The Solvability of Interpretability Evaluation Metrics EACL 2023
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability EMNLP 2021
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? ACL 2020
Comparing Automatic and Human Evaluation of Local Explanations for Text Classification NAACL 2018
Reading Tea Leaves: How Humans Interpret Topic Models NIPS 2009