arXiv:2603. 10742v4 Announce Type: replace Abstract: Data leakage has been identified in 648 published papers across 30 scientific fields.
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
arXiv:2608. 10137v1 Announce Type: cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step.
arXiv:2607. 18357v1 Announce Type: cross Abstract: Large language models now write a growing share of the world's code, increasingly inside agents and serving systems that compile, execute, or dispatch generated code without line-by-line review.
arXiv:2606. 02991v1 Announce Type: cross Abstract: We introduce TypewriterLM, a 7.
arXiv:2607. 03158v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to implement algorithms from research manuscripts, but papers often leave implementation choices implicit.
arXiv:2607. 20455v1 Announce Type: cross Abstract: Human-annotated data remains fundamental to training frontier Large Language Models (LLMs).
arXiv:2608. 04980v1 Announce Type: cross Abstract: We show that tiny transformers can profitably employ a simple form of Chain of Thought, which we call protoreasoning, allowing us to study step-by-step reasoning on ~1M-parameter models and opening up opportunities for much more detailed experimentation and analysis than is feasible for larger models.
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
arXiv:2606. 02632v1 Announce Type: cross Abstract: Modern Machine Learning (ML) and Artificial Intelligence (AI) models, especially large language models (LLMs), are increasingly used to generate scientific hypotheses and mechanistic explanations from observational data.
arXiv:2608. 05493v1 Announce Type: cross Abstract: Language models (LMs) are increasingly used to interact with external services via programs written in domain-specific languages (DSLs).
arXiv:2603. 28345v3 Announce Type: replace-cross Abstract: LLM API calls have become a standard programming primitive, but they create a program boundary that disrupts traditional dataflow analysis.
arXiv:2606. 11267v1 Announce Type: new Abstract: Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based science, yet detection tools require training code, external data, or domain expertise.