Later LLM layers align better with human cognitive effort in syntactic ambiguity than early layers do, indicating dual processing modes and complementary benefits from multi-layer probability updates.
Classification and Clustering of Arguments with Contextualized Word Embeddings
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
A domain-agnostic framework extracts perspectives from book reviews showing LLMs underrepresent rarer viewpoints relative to human text.
citing papers explorer
-
Dual Alignment Between Language Model Layers and Human Sentence Processing
Later LLM layers align better with human cognitive effort in syntactic ambiguity than early layers do, indicating dual processing modes and complementary benefits from multi-layer probability updates.
-
Evaluating Pluralism in LLMs through Latent Perspectives
A domain-agnostic framework extracts perspectives from book reviews showing LLMs underrepresent rarer viewpoints relative to human text.