arXiv subjects

Rasmus Blanck

Publications and source records attributed to Rasmus Blanck.

2 recordsLinked to original sources

arXiv2026

Reverse-engineering NLI: A study of the meta-inferential properties of Natural Language Inference

Natural Language Inference (NLI) has been an important task for evaluating language models for Natural Language Understanding, but the logical properties of the task are poorly understood and often mischaracterized. Understanding the notion of inference captured by NLI is key to interpreting model performance on the task. In this paper we formulate three possible readings of the NLI label set and perform a comprehensive analysis of the meta-inferential properties they entail. Focusing on the SNLI dataset, we exploit (1) NLI items with shared premises and (2) items generated by LLMs to evaluate models trained on SNLI for meta-inferential consistency and derive insights into which reading of the logical relations is encoded by the dataset.

cs.CL↗

arXiv2021

Hierarchical incompleteness results for arithmetically definable extensions of fragments of arithmetic

There has been a recent interest in hierarchical generalisations of classic incompleteness results. This paper provides evidence that such generalisations are readibly obtainable from suitably hierarchical versions of the principles used in the original proof. By collecting such principles, we prove hierarchical versions of Mostowski's theorem on independent formulae, Kripke's theorem on flexible formulae, and a number of further generalisations thereof. As a corollary, we obtain the expected result that the formula expressing "$T$ is $Σ_n$-ill" is a canonical example of a $Σ_{n+1}$ formula that is $Π_{n+1}$-conservative over $T$.

math.LO↗