🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🚨 New Pre-Print! We show that in-context learning can steer LLM rankers to satisfy multiple objectives at once, relevance and fairness/diversity, without any parameter updates. Work done jointly with Nilanjan Sinhababu from IIT Kharagpur and Debasis Ganguly. 🧵 Below!

Full details in our paper. I'd love to discuss broader applications of this work in Padua at #SIGIR2025 in July, so reach out! In the meantime, have a read! ➡️ arxiv.org/abs/2505.17736

Control ranking behavior with simple demonstration engineering: An in-context learning approach demonstrating how targeted example rankings can be used to flexibly adapt to different objectives. I thank Andrew Parry Debasis Ganguly & Prof. Pabitra Mitra for their valuable contribution