English

Oddballness: universal anomaly detection with language models

Computation and Language 2024-09-06 v1

Abstract

We present a new method to detect anomalies in texts (in general: in sequences of any data), using language models, in a totally unsupervised manner. The method considers probabilities (likelihoods) generated by a language model, but instead of focusing on low-likelihood tokens, it considers a new metric introduced in this paper: oddballness. Oddballness measures how ``strange'' a given token is according to the language model. We demonstrate in grammatical error detection tasks (a specific case of text anomaly detection) that oddballness is better than just considering low-likelihood events, if a totally unsupervised setup is assumed.

Keywords

Cite

@article{arxiv.2409.03046,
  title  = {Oddballness: universal anomaly detection with language models},
  author = {Filip Graliński and Ryszard Staruch and Krzysztof Jurkiewicz},
  journal= {arXiv preprint arXiv:2409.03046},
  year   = {2024}
}
R2 v1 2026-06-28T18:34:34.799Z