1BOneBench

Search OneBench

Search signals, briefings, benchmarks and glossary terms.

Back to Signals
RESEARCHInvestigateNEXT 12 MONTHS

Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders

arXiv cs.CL — Computation and Language

Factual evidence

What the source reports

Research reveals LLM-based recommender systems are vulnerable to position bias, enabling attackers to promote items by reordering candidates.

Open source

OneBench interpretation

Institutional assessment

So what

Positional bias in LLM rerankers creates an attack surface for manipulating recommendation outputs in financial product surfacing.

Do what

Add `promo@k` metrics to your model validation framework for LLM-based recommender systems.