Generative AI systems powered by Large Language Models have become increasingly popular in recent years. Lately, due to the risk of providing users with unsafe information, the adoption of those systems in safety-critical domains has raised significant concerns. To respond to this situation, input-output filters, commonly called guardrail models, have been proposed to complement other measures, such as model alignment. Unfortunately, the lack of a standard benchmark for guardrail models poses significant evaluation issues and makes it hard to compare results across scientific publications. To fill this gap, we introduce GuardBench, a large-scale benchmark for guardrail models comprising 40 safety evaluation datasets. To facilitate the adoption of GuardBench, we release a Python library providing an automated evaluation pipeline built on top of it. With our benchmark, we also share the first large-scale prompt moderation datasets in German, French, Italian, and Spanish. To assess the current state-of-the-art, we conduct an extensive comparison of recent guardrail models and show that a general-purpose instruction-following model of comparable size achieves competitive results without the need for specific fine-tuning.

Personalization of search results has gained increasing attention in the past few years, also thanks to the development of Neural Networks-based approaches for Information Retrieval. Recent works have proposed to build user models at query time by leveraging the Attention mechanism, which allows weighing the contribution of the user-related information w.r.t. the current query.This approach allows giving more importance to the user’s interests related to the current search performed by the user.In this paper, we discuss some shortcomings of the Attention mechanism when employed for personalization and introduce a novel Attention variant, the Denoising Attention, to solve them.Denoising Attention adopts a robust normalization scheme and introduces a filtering mechanism to better discern among the user-related data those helpful for personalization.Experimental evaluation shows improvements in MAP, MRR, and NDCG above 15% w.r.t. other Attention variants at the state-of-the-art.