Papers for

news verification units

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Subspace interaction improves spotting odd words in text efficiently

SIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detection

Abstract: Token-level text anomaly detection, as an emerging trend of text anomaly detection, moves beyond coarse-grained document-level detection by localizing anomalous tokens within text. By providing fine-grained abnormality prediction, token-level text anomaly detection plays a critical role in various real-world applications, such as spam filtering and fake news detection. However, existing methods still rely on the global distance calculation for scoring, during which the local anomaly signals are severely diluted by numerous redundant normal feature dimensions. Moreover, pre-trained language models used in these methods inevitably smooth out surface anomalies, further limiting their effectiveness in token-level anomaly detection. To address these limitations, we propose a Subspace Interaction-based Method (SIM for short) for token-level text anomaly detection. To prevent local signal dilution, SIM adopts a subspace interaction-based anomaly detector, which decouples high-dimensional token embeddings into multiple low-dimensional ones, amplifying localized anomaly signals hidden within specific dimensions. To counteract the over-smoothing effect, we design a hard pseudo-anomaly generation module to construct pseudo-anomalous tokens, simulating the subtle anomalies obscured by semantic smoothing. Also, a probabilistic boundary loss is developed to standardize anomaly scores into statistical distances, effectively enforcing anomalous instances to deviate significantly from the normal distribution center. Extensive experiments on multiple benchmark datasets verify the effectiveness of SIM and demonstrate its remarkable efficiency, robustness, and interpretability. The source code is available at: https://github.com/yankehan/SIM-TAD.

Tue 8 SeptMachine Learning
The gist
Detecting unusual or suspicious words inside texts is important for spotting things like spam or fake news. Existing methods often miss these odd words because they get lost when looking at the whole text all at once. The authors propose SIM, a new approach that looks at smaller parts of the word representations to better catch strange signals. They also create fake anomalies to help the system learn what unusual words look like despite smooth language models hiding them. Testing shows SIM works well, is fast, and easy to interpret.
Open → 2609.08200v1