🔥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

Need to address my earlier tweet: the #ACL2025 deadline has now been updated to February 15. Be sure to check out the updated CFP for all the details at 2025.aclweb.org/calls/main_con…. Thank you for your understanding as we navigate these changes! 📝✨

Very interesting anecdote shared by the boss of NVIDIA (world's most valuable company which is worth 3.4 Trillion dollars) when he met the Prime Minister of the World's largest democracy, India, Narendra Modi

ConQRet: Benchmarking Fine-Grained Evaluation of Retrieval Augmented Argumentation with LLM Judges Introduces a benchmark for evaluating retrieval-augmented argumentation systems through LLM-based judges. 📝arxiv.org/abs/2412.05206 👨🏽‍💻github.com/emory-irlab/co…

Best poster moment at #NeurIPS2024

Etymology of the name Dr. Manmohan Singh 1/3

There were many great responses to my recent post about the tension between thinker mode and manager mode, but the most intriguing was this essay arguing that you can't do both simultaneously, and yet need to do each of them to be good at the other, so the solution is to be on a

+1

To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation. arxiv.org/abs/2501.09292

💎 ...

🚨 IJCNLP-AACL 2025 will be held in IIT Bombay, India! 📅 Date: 20th - 24th December 2025 🏢 Venue: Victor Menezes Convention Centre (VMCC), IIT Bombay, Mumbai, India 🗺️ Map Location: maps.app.goo.gl/Cd9JPMaiWr7TDj… In the following days, more information will be made available!

Dynamic retrieval, guided by uncertainty, improves efficiency in retrieval-augmented generation. This paper enhances Retrieval Augmented Generation (RAG) efficiency by dynamically invoking retrieval only when the LLM is uncertain. This reduces unnecessary retrievals, especially

Paper Title: "To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation" Generated below podcast on this paper with Google's Illuminate.

🚀 IndiaAI Call for Proposals: Building India's own Foundational AI Models! 🔹 Develop indigenous LLMs & SLMs tailored for India 🔹 Ensure diverse & contextual relevance 🔹 Solve India-specific challenges across key sectors

GEM is so back! Our workshop for Generation, Evaluation, and Metrics is coming to an ACL near you. Evaluation in the world of GenAI is more important than ever, so please consider submitting your amazing work. CfP can be found at gem-benchmark.com/workshop

→ Design benchmarks that measure how models behave, not just task performance. 2/n

We're back with #SMM4H 2025 Workshop and Shared Task co-located at ICWSM🎯 Abeed Sarker, PhD, Jeanne Powell, PhD, and I will be organizing Task 2. So feel free to reach out! Registration form📅 docs.google.com/forms/d/e/1FAI…

Generative Product Recommendations for Implicit Superlative Queries Amazon introduces a 4-point schema called SUPERB for annotating the best product candidates when users make indirect superlative queries, paired with LLM-based product annotations. 📝arxiv.org/abs/2504.18748

GEM 2025 ARR-reviewed deadline extended to May 17 - Pre-reviewed ARR papers should be submitted by filling this short form: lnkd.in/eV8FW_Cm 📅 May 17: Pre-reviewed (ARR) commitment deadline. 📅 May 25: Notification of acceptance. 📅 June 12: Camera-ready deadline.