Christina Ma

While we’re building amazing new human-AI systems, how do we actually know if they work well for people? In our #ACL2025 Findings Paper, we introduce SPHERE, a framework for making evaluations of human-AI systems more transparent and replicable. ✨aclanthology.org/2025.findings-…

What’s next for prompt engineering? 🚀 @1000seagull et al. introduce ROPE —a new paradigm where humans focus on writing clear, complete requirements for LLMs. ROPE training shows 20× better gains than traditional methods. Paper: dl.acm.org/doi/10.1145/37… #LLM #PromptEngineering #AI