Cover Image

Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Boguraev, Sasha, Mahowald, Kyle
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
by: Boguraev, Sasha, et al.
Published: (2025)

France or Spain or Germany or France: A Neural Account of Non-Redundant Redundant Disjunctions
by: Boguraev, Sasha, et al.
Published: (2026)

Models Can and Should Embrace the Communicative Nature of Human-Generated Math
by: Boguraev, Sasha, et al.
Published: (2024)

Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs
by: Weissweiler, Leonie, et al.
Published: (2025)

A suite of LMs comprehend puzzle statements as well as humans
by: Goldberg, Adele E, et al.
Published: (2025)

You Can't Fight in Here! This is BBS!
by: Futrell, Richard, et al.
Published: (2026)

Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs
by: Misra, Kanishka, et al.
Published: (2024)

For Generated Text, Is NLI-Neutral Text the Best Text?
by: Mersinias, Michail, et al.
Published: (2023)

How Linguistics Learned to Stop Worrying and Love the Language Models
by: Futrell, Richard, et al.
Published: (2025)

Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs
by: Lederman, Harvey, et al.
Published: (2024)

Emergent Introspection in AI is Content-Agnostic
by: Lederman, Harvey, et al.
Published: (2026)

The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models
by: Drucker, Daniel, et al.
Published: (2026)

Participle-Prepended Nominals Have Lower Entropy Than Nominals Appended After the Participle
by: Denlinger, Kristie, et al.
Published: (2024)

Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently
by: Misra, Kanishka, et al.
Published: (2024)

Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP
by: Rozner, Josh, et al.
Published: (2021)

Convergence and Divergence of Language Models under Different Random Seeds
by: Fehlauer, Finlay, et al.
Published: (2025)

Language Models Fail to Introspect About Their Knowledge of Language
by: Song, Siyuan, et al.
Published: (2025)

Constructions are Revealed in Word Distributions
by: Rozner, Joshua, et al.
Published: (2025)

On Language Models' Sensitivity to Suspicious Coincidences
by: Padmanabhan, Sriram, et al.
Published: (2025)

Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models
by: Yao, Qing, et al.
Published: (2025)

Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways
by: Govindarajan, Venkata S, et al.
Published: (2023)

Privileged Self-Access Matters for Introspection in AI
by: Song, Siyuan, et al.
Published: (2025)

semantic-features: A User-Friendly Tool for Studying Contextual Word Embeddings in Interpretable Semantic Spaces
by: Ranganathan, Jwalanthi, et al.
Published: (2025)

Tree Transformers are an Ineffective Model of Syntactic Constituency
by: Ginn, Michael
Published: (2024)

Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias
by: Govindarajan, Venkata S, et al.
Published: (2023)

Do they mean 'us'? Interpreting Referring Expressions in Intergroup Bias
by: Govindarajan, Venkata S, et al.
Published: (2024)

Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision
by: Yoshida, Ryo, et al.
Published: (2024)

Are BabyLMs Second Language Learners?
by: Edman, Lukas, et al.
Published: (2024)

Language models align with human judgments on key grammatical constructions
by: Hu, Jennifer, et al.
Published: (2024)

Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations
by: Lindemann, Matthias, et al.
Published: (2024)

How to Make LMs Strong Node Classifiers?
by: Xu, Zhe, et al.
Published: (2024)

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
by: Prashanth, USVSN Sai, et al.
Published: (2024)

Investigating Syntactic Biases in Multilingual Transformers with RC Attachment Ambiguities in Italian and English
by: Kamerath, Michael, et al.
Published: (2025)

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
by: Bochkov, A.
Published: (2025)

SAP: Syntactic Attention Pruning for Transformer-based Language Models
by: Lee, Tzu-Yun, et al.
Published: (2025)

A Systematic Study of Compositional Syntactic Transformer Language Models
by: Zhao, Yida, et al.
Published: (2025)

Compositional preference models for aligning LMs
by: Go, Dongyoung, et al.
Published: (2023)

Humans and transformer LMs: Abstraction drives language learning
by: Jian, Jasper, et al.
Published: (2026)

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
by: Alnuhait, Deema, et al.
Published: (2024)

Beyond Pattern Recognition: Probing Mental Representations of LMs
by: Miller, Moritz, et al.
Published: (2025)