AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis

Hangting Ye, Jinmeng Li, He Zhao, Mingchen Zhuge, Dandan Guo, Yi Chang, Hongyuan Zha

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Data and hallucination detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LLM-DAS synthetic hard anomaliesOCSVM · 36 tabular AD datasetsAUC-PR: +0.0723 AUC-PR (84.49%)Improved
add LLM-DAS synthetic hard anomaliesPCA · 36 tabular AD datasetsAUC-PR: .5975 -> improvement .0402 (21.50%), win 30 / 36Improved
add LLM-DAS synthetic hard anomaliesIForest · 36 tabular AD datasetsAUC-ROC: .7555 -> improvement .0385 (10.90%), win 28 / 36Improved
add LLM-DAS synthetic hard anomaliesECOD · 36 tabular AD datasetsAUC-PR: .5376 -> improvement .0512 (23.05%), win 28 / 36Improved
add LLM-DAS synthetic hard anomaliesDRL · 36 tabular AD datasetsAUC-ROC: .8509 -> improvement .0272 (3.79%), win 21 / 36Improved
use OCSVM-specific instead of PCA-specific synthesis code (ablation)OCSVM · Cross-detector synthesis on OCSVM (7 datasets)AUC-PR average change: -0.0213 -> +0.0295Improved
use OCSVM-specific instead of IForest-specific synthesis code (ablation)OCSVM · Cross-detector synthesis on OCSVM (7 datasets)AUC-PR average change: +0.0076 -> +0.0295Improved
use mismatched PCA code on OCSVM (ablation)OCSVM · VowelsAUC-PR change: -0.1899Hurt
replace detector-aware prompt with generic prompt, no-score-access prompt, or random seed selection (ablation)LLM-DAS · 36 tabular AD datasetsAUC-PRImproved
use random outlier synthesis instead of LLM-DASDRL · 36 tabular AD datasetsAUC-PRHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy