Tag
This research investigates how multilingual large language models internally handle subject-verb agreement across languages, finding that models reuse shared computational structure for languages with overt inflection, indicating cross-lingual overlap in morphosyntactic processing.
TokenScope is an interactive interpretability tool for decoder-only large language models that provides token-level metrics, attention patterns, and counterfactual branching during code generation, enabling systematic investigation of model behavior.
ArXiv preprint identifies low information density as the root cause of NER performance collapse on noisy user-generated content and introduces the Window-Aware Optimization Module (WOM) that boosts F1 by up to 4.5% on WNUT2017.