2 citations · 3 across the 6 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CY2025
Phare: A Safety Probe for Large Language Models
Pierre Le Jeune, Benoît Malézieux, Weixuan Xiao +1
Ensuring the safety of large language models (LLMs) is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We…
cs.CY2025★ 2 cited
RealHarm: A Collection of Real-World Language Model Application Failures
Pierre Le Jeune, Jiaen Liu, Luca Rossi +1
Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches d…