arXiv Computation and Language
A Data-free Universal Prior over Syntactic Structures
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Sep 15
Universal Topological Regularity of Syntactic Structures
arXiv:2302.00129v2 Announce Type: replace Abstract: Despite their widespread use, the principles governing the organisation of syntactic dependency trees remain poorly understood. I analyse dependenc...
arXiv AI
Sep 7
Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation
The paper studies structural priming in language model production by conducting controlled sentence‑completion experiments on dative constructions. Results show that language models exhibit priming effects, especially when sentences are semantically coherent, with stronger relative increases for double‑object datives and larger absolute increases for prepositional‑object datives. The study also finds that primed completions involve more lexico‑semantic repetition, indicating that priming operates across syntactic, lexical, and semantic levels.
arXiv Computation and Language
3d ago
The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts
arXiv:2609.24821v1 Announce Type: new Abstract: The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-relate...
arXiv Machine Learning
Jun 9
Phase transition in large language models and the criticality of natural languages
arXiv:2406. 05335v3 Announce Type: replace-cross Abstract: Generation of text and speech in natural languages can be modeled as a stochastic process.
arXiv AI
Jun 3
Identifying Quantum Structure in AI Language: Evidence for Evolutionary Convergence of Human and Artificial Cognition
arXiv:2511. 21731v2 Announce Type: replace-cross Abstract: We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects.
arXiv AI
Sep 3
Induction and Inquiry via Probabilistic Reasoning over Language and Code
The paper introduces a computational model that encodes symbolic knowledge as mental programs combining natural language and source code, and uses LLM-guided Bayesian learning to sequentially infer these programs. It demonstrates that this approach satisfies data‑efficiency, uncertainty handling, and flexibility, reproducing human inductive learning and active inquiry behaviors such as anchoring and garden‑pathing. In contrast, pure LLMs and classic Bayesian models either fail the task, do not match human behavior, or require prohibitive computational resources.