20 results for “Statistical knowledge”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper proposes an architecture for sequential statistical procedures that can be used in various applications.
This paper demystifies neural networks for classical statisticians by describing networks that approximate linear regression and common customizations.
Lisa Oakley, Sam Stites, Cameron Moy, Steven Holtzen +2 more
This paper proposes a Bayesian framework to enhance membership inference attacks against released statistics by incorporating prior knowledge about the population's attribute dependency structure, out…
The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…
This paper presents an epistemic logic framework for studying randomized algorithms in distributed computation.
HuiMing Fan, Xiao Wang, Zheng Chu, Qianyu Wang +4 more
The paper argues that current search agents often verify existing knowledge rather than genuinely searching, and introduces LiveBrowseComp, a new benchmark to measure true evidence-driven discovery.
This paper formalizes test-time training (TTT) as a problem of sampling from a given probability measure and shows a quadratic lower bound on the query complexity of sampling.
This paper proposes a method to evaluate the correctness of LLM-generated COBOL summaries without human references.
The paper introduces Factual Density (FD*), a novel retrieval signal that measures the proportion of verified facts, demonstrating that optimizing RAG retrieval based on this density significantly imp…
This paper provides non-asymptotic and explicit estimates for the exponential deviation inequalities of the HyperLogLog estimator.
This paper evaluates the ability of large language models to recover and express evidence grades from clinical claims, finding that while they can recover the grades, they do not consistently express…
This paper investigates the use of strategically diverse data in self-training for LLMs, showing that diversity of approaches can matter more than correctness or teacher scale.
The paper generalizes the convex-algebra interchange axiom to support full Bayesian conditioning.
This paper proposes statistical principles for using synthetic data in scientific research with provable validity guarantees.