Tag
This paper uses causal interventions to investigate syntactic mechanisms in multilingual language models, revealing cross-lingual transfer that is graded based on typological similarity.
The paper proposes a three-dimensional typology of agency for advanced AI systems, distinguishing moral from legal agency and classifying eight instantiations as conventional, contested, or controversial.
This paper presents a modular framework for generating artificial lexicons that are pronounceable, typologically plausible, and semantically structured, using phoneme inventories from PHOIBLE and probabilistic grammars, outperforming deterministic baselines.
This paper investigates brain-LLM alignment across English, Chinese, and French using fMRI data and multiple LLMs, finding that training-language dominance and typological distance, not an inherent English advantage, drive alignment patterns.