Structural probes on UD-invariant wh-movement stimuli reveal phase-count gradients and phase-internal cohesion effects in 12-13 of 13 LLMs, indicating syntactic abstractions beyond UD annotations.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Language models employ a highly localized shared mechanism for filler-gap dependencies but no unified mechanism for NPI licensing, and activation patching generalizes better than supervised alignment search.
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.
Causal interventions reveal that coordination islands block filler-gap mechanisms in Transformers in a gradient way matching humans, yielding the hypothesis that 'and' encodes relational dependencies differently in extractable vs. conjunctive uses.
mGRADE uses learnable-spaced convolutions shown to be equivalent to delay embeddings plus a lightweight gated recurrent component to achieve low-memory multi-timescale sequence modeling.
citing papers explorer
-
Probing Minimalist Phase Structure in LLMs: What Universal Dependencies Cannot Represent
Structural probes on UD-invariant wh-movement stimuli reveal phase-count gradients and phase-internal cohesion effects in 12-13 of 13 LLMs, indicating syntactic abstractions beyond UD annotations.
-
Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models
Language models employ a highly localized shared mechanism for filler-gap dependencies but no unified mechanism for NPI licensing, and activation patching generalizes better than supervised alignment search.
-
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.
-
Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs
Causal interventions reveal that coordination islands block filler-gap mechanisms in Transformers in a gradient way matching humans, yielding the hypothesis that 'and' encodes relational dependencies differently in extractable vs. conjunctive uses.