Attribution methods localize anchoring signals in Qwen and Llama models; edge-level circuits transfer within a model but show sparse transfer from base to instruction-tuned variants.
ArXiv:2508.11214 [cs]
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Language models can provide scientific insights into human language beyond mere string statistics, and the language sciences should pursue a broader research program that integrates computational and theoretical approaches.
citing papers explorer
-
Localizing Anchoring Pathways in Language Models
Attribution methods localize anchoring signals in Qwen and Llama models; edge-level circuits transfer within a model but show sparse transfer from base to instruction-tuned variants.
-
You Can't Fight in Here! This is BBS!
Language models can provide scientific insights into human language beyond mere string statistics, and the language sciences should pursue a broader research program that integrates computational and theoretical approaches.