Show HN: Phare: A Safety Probe for Large Language Models https://ift.tt/Zl87VRe

Show HN: Phare: A Safety Probe for Large Language Models We've just published a benchmark and accompanying paper on arXiv that challenges conventional leaderboard-driven LLM evaluation. Phare focuses on factual reliability, prompt sensitivity, multilingual support, and how models handle false premises like issues that actually matter when you're building serious applications. Some insights: - Preference scores ≠ factual correctness. - Framing effects can cause models to miss obvious falsehoods. - Safety metrics like sycophancy and stereotype reproduction show surprising results across popular models. Would love feedback from the community. https://ift.tt/UmGwKpY May 21, 2025 at 03:08AM