AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis
Factual evidence
What the source reports
Researchers introduced AMLworld-Compact, a stratified downsampling method that reduces LLM evaluation costs for anti-money laundering.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 12 October 2026
- Collected by OneBench
- 13 Oct 2026, 03:01 UK
Stored source excerpt
arXiv:2610.13627v1 Announce Type: new Abstract: Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
Graph-prompting LLMs for transaction monitoring is computationally expensive; importance sampling enables scalable evaluation without sacrificing illicit transaction coverage.
Do what
Review the evaluation sampling methodology with teams assessing large language models for anti-money laundering and transaction monitoring.