Oddballness: universal anomaly detection with language models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916382802706432 |
|---|---|
| author | Graliński, Filip Staruch, Ryszard Jurkiewicz, Krzysztof |
| author_facet | Graliński, Filip Staruch, Ryszard Jurkiewicz, Krzysztof |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03046 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Oddballness: universal anomaly detection with language models Graliński, Filip Staruch, Ryszard Jurkiewicz, Krzysztof Computation and Language 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. |
| title | Oddballness: universal anomaly detection with language models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.03046 |