Papers with anomaly detection tasks
LogRules: Enhancing Log Analysis Capability of Large Language Models through Rules (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) exhibit hallucinations when analyzing logs due to the implicit knowledge and rules in logs that LLMs cannot capture. |
| Approach: | They propose a lightweight log analysis framework that generates and utilizes rules through LLMs. |
| Outcome: | The proposed framework outperforms LLM-based methods in log parsing and anomaly detection tasks and achieves better performance compared to case-based approaches. |
VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have greatly influenced the development of Large Multi-modal Video Models. |
| Approach: | They propose a benchmark to assess the proficiency of Large Multi-modal Video Models (LMMs) in detecting and localizing anomalies and inconsistencies in videos. |
| Outcome: | The proposed benchmark assesses the proficiency of Video-LMMs in detecting and localizing anomalies and inconsistencies in videos. |
Enhancing Two Steps Textual Anomaly Detection through Anisotropy Mitigation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to anomaly detection focus on embeddings from pre-trained models . however, the geometric properties of pre-training embedders can hinder detection algorithms . |
| Approach: | They propose to apply anomaly detection algorithms to embeddings from pre-trained models to improve accuracy. |
| Outcome: | The proposed approach improves similarity-trained models by adapting embeddings to assumptions made by classical detection algorithms. |