LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
Tracing multilingual factual knowledge acquisition in pre- training
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Introduces the MEA benchmark for multi-target cross-lingual summarization across 24 languages and demonstrates that activation steering from English summarization representations improves performance.
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.
citing papers explorer
-
LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
LMs store facts in task-specific parameter subsets, shown by inconsistent emergence across tasks during training and distinct localized parameters for the same fact.
-
Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization
Introduces the MEA benchmark for multi-target cross-lingual summarization across 24 languages and demonstrates that activation steering from English summarization representations improves performance.
-
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.