conftrace_

language model interpretability

6 papers

Explore in graph

Co-occurring keywords

language model (4599) edge attribution patching (1) position-aware circuit (1) model mechanism analysis (1) activation steering (45) gradient-based saliency (10) neural network (6616) board game (18) syllogistic reasoning (12) sentence editing (2)

Papers

Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models EACL 2026
Position-aware Automatic Circuit Discovery ACL 2025
Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement EMNLP 2025
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NIPS 2024
Interpretability of Language Models via Task Spaces ACL 2024
An Investigation of Language Model Interpretability via Sentence Editing EMNLP 2021