AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

$f$-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash Harandi, Trung Le

ICML 2026 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 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
replace one-shot SFT (AnoLLM) with f-divergence self-playAnoLLM SmolLM-135M · Six-dataset benchmarkAUC-ROC (%): 76.5% -> 84.6%Improved
replace one-shot SFT (AnoLLM) with f-divergence self-playAnoLLM SmolLM-360M · Six-dataset benchmarkAUC-ROC (%): 77.8% -> 85.4%Improved
replace one-shot SFT (AnoLLM) with f-divergence self-playAnoLLM SmolLM-1.7B · Six-dataset benchmarkAUC-ROC (%): 77.7% -> 83.5%Improved
replace one-shot SFT (AnoLLM) with f-divergence self-playAnoLLM SmolLM-1.7B · Six-dataset benchmarkF1 (%): 40.1% -> 48.0%Improved
replace one-shot SFT (AnoLLM) with f-divergence self-playAnoLLM SmolLM-1.7B · FakejobAUC-PR (%): 31.2% -> 30.0%Hurt
replace one-shot SFT (AnoLLM) with f-divergence self-playAnoLLM SmolLM-360M · VehicleF1 (%): 17.4% -> 19.6%Hurt
add self-play iterations (up to iter-3) after SFT (ablation)DiSPaT SmolLM-135M · Fakejob, Vehicle, 20 Newsgroups, EcoliAUC-ROCMixed
use KL conjugate e^v-1 instead of identity (SPIN) conjugate (ablation)DiSPaT SmolLM-135M · 4 datasets avgAUC-ROC (%): 83.7% -> 85.7%Improved
use KL conjugate e^v-1 instead of identity (SPIN) conjugate (ablation)DiSPaT SmolLM-135M · 4 datasets avgF1 (%): 44.9% -> 52.7%Improved
use KL conjugate e^v-1 instead of identity (SPIN) conjugate (ablation)DiSPaT SmolLM-135M · 4 datasets avgAUC-PR (%): 44.6% -> 50.5%Improved
use reverse KL instead of identity conjugate (ablation)DiSPaT SmolLM-135M · 4 datasets avgAUC-ROC (%): 83.7% -> 84.4%Improved
use squared Hellinger instead of identity conjugate (ablation)DiSPaT SmolLM-135M · 4 datasets avgAUC-ROC (%): 83.7% -> 84.8%Improved

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