← Back to all news
arXiv Computation and Language By Xiang Ding

Language Models Keep Abandoned Analyses: Residue and Adaptation after Garden-Path Sentences

Read the original on arXiv Computation and Language →

The study investigates whether large language models retain traces of abandoned syntactic analyses after encountering garden‑path sentences. Across 24 models ranging from 124 M to 70 B parameters, the authors find that a residue of the initial, incorrect analysis influences later object attachment, while an adaptation toward the resolved structure scales with disambiguation error. Activation‑patching experiments show that the residue is carried by noun‑phrase states computed under the object analysis, and that overriding these states largely removes the effect.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Jul 10

How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism

arXiv:2607. 07891v1 Announce Type: cross Abstract: Roy Harris's Integrationist linguistics offers a compelling critique of the referentialist tradition embedded deep at the heart of computational approaches to language, arguing that language is not a code that maps onto a pre-given world but a situated, bipartite activity oriented toward prospective joint action.

By J. Mark Bishop, Stephen J. Cowley
llmsnlp
More like this →
Hugging Face Trending Papers
Aug 20

Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models

The paper investigates how periodic subject changes—termed interruptions—affect the perceived novelty and coherence of text generated by base language models. By inserting a new subject every few hundred tokens into a stream that otherwise repeats, the authors find that judged surprise increases by 1.2 to 1.4 points and connection by 0.8 points compared to habituation alone. The study also reports that such interruptions do not produce integrated documents, and that the effect is robust across different models and evaluation protocols.

llms
More like this →
arXiv Machine Learning
Sep 11

Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models

The paper investigates whether language models can identify sentences from their training data by using exact duplication counts from publicly released corpora for two model families, OLMo‑2 and Pythia. It finds that for typical duplication levels, models show only a weak trace of exposure, with a rank correlation near –0.08, and that strong signals only appear when a sentence appears roughly a thousand times, at which point fame rather than memory dominates. The study also demonstrates that common membership tests can be misleading, as changing a single word does not alter the model’s preference, and that controlling for register can significantly improve detector performance.

By Arman Nik Khah
llms
More like this →