Per-head attention contributions to the residual stream serve as strong linear features for classifying relational knowledge in LLMs, with probe accuracy correlating to relation specificity and signal distribution.
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.
citing papers explorer
-
Tracing Relational Knowledge Recall in Large Language Models
Per-head attention contributions to the residual stream serve as strong linear features for classifying relational knowledge in LLMs, with probe accuracy correlating to relation specificity and signal distribution.
-
REMOD: Relation Extraction for Modeling Online Discourse
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.