🔥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

Leonardo Ranaldi and I, presenting our Curriculum LearningLRC at RANLP2023 in Varna, Bulgaria 🚀❤️ #RANLP #NLP RANLP 2023

HumanCentricART Università di Roma Tor Vergata working hard for challenges in Language Tech - Elena Sofia Ruzzetti Leonardo Ranaldi Giulia Pucci presenting at RANLP 2023

Schools and LLMs: Are you ready for the challenge? Two 1-year Research Fellowships We offer an uncompetitive salary ;-) Yet, YOU can help to integrate LLMs to prepare "biological brains" for a vibrating future. DM us!

#NLProc Willing to evaluate "data contamination" in Transformers? We have a metric: PreCog! Exploring the Relation between Memorization and Performance in Pre-trained Language Models soon on ACL archive (presented at #RANLP2023): arxiv.org/pdf/2305.04673…

Do you want to discuss your views on #Psycoanalysis for #LLMs? Are you more interested in #Psychiactric of #LLMs? Or in performing #ArtificialBrain #Surgery? #NLProc We are ready to interact you! The #Humancentric #ArtificialIntelligence Università di Roma Tor Vergata has a new X accout

Congratulations, Prof!

Hey, AILC_NLP, we are arriving disentraining in a few minutes! #clicit2023 #NLProc Elena Sofia Ruzzetti Dario Onorati leonardo FedericoRanaldi Giulia Pucci and Davide Venditti Eager to learn from and to network with #clicit2023's participants!

Wow! Camoscio! Good shot Andrea Santilli #clicit2023 AILC_NLP

Are all languages equal? Who knows? AILC_NLP CLiC-it Conference Leonardo Ranaldi Giulia Pucci Fabio Massimo Zanzotto #NLProc

#EMNLP2023 challenge Tag a paper you see with #PsycoanalysisOfLLMs if you think it is

It's nearly #Xmas2023 #LLM s and #ChatGPT should become better persons with less #BIAS Let's measure it! The paper : aclanthology.org/2023.findings-… The dataset : huggingface.co/datasets/Human… #NLProc at #EMNLP2023 Elena Sofia Ruzzetti Dariutso Davide Leonardo Ranaldi Fabio Massimo Zanzotto

What are the layers responsabile for Syntax and Morphology encoding? We propose a comparative analysis of Bert's weight matrices. A big thank to my team Human-Centric ART @unitorvergata #EMNLP2023 #LLM #Bert #noprobing #syntax #morphology aclanthology.org/2023.findings-…

#Fairness and Instruction-following #LLMs : a test P-AT Hugging Face : huggingface.co/datasets/Human… P-AT EMNLP 2025 : aclanthology.org/2023.findings-… #NLProc #chatgpt4 w/ Elena Sofia Ruzzetti Dariutso Davide Leonardo Ranaldi Fabio Massimo Zanzotto

Hey #NLProc! Happy to share our work that will be presented next week at #EACL2024! We study the impact of in-family learning demonstrations for aligning multi-step reasoning abilities between LLMs. Link: aclanthology.org/2024.eacl-long… See you in Malta! André Freitas Idiap Research Institute

Waiting for Leonardo Ranaldi to present his paper at #EACL2024 in the beautiful Malta (Radisson blu, Carlson Ballroom, 5th floor) 🚀 "Aligning Large and Small Language Models via Chain-of-Thought Reasoning": aclanthology.org/2024.eacl-long… 🚀🚀🚀

Summary of Hinrich Schütze’s keynote at #EACL2024! Cannot agree on tough and exciting challenges!

At last, a curriculum learning that works, one for pretraining and another for instruction tuning Leonardo Ranaldi Giulia Pucci André Freitas Fabio Massimo Zanzotto aclanthology.org/2024.lrec-main… aclanthology.org/2023.ranlp-1.1…

#UnboxingTransformer If you are in #ACL2024NLP #ACL2024, we are sure: 1) you can try to solve our challenge uniroma2-my.sharepoint.com/:b:/g/personal… 2) and, then, you can apply to the OPEN POSITION in our lab. Competitive salary in an astonishing location #ML #NLProc pica.cineca.it/uniroma2/f4-20…

Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations Improves RAG models by generating contrastive explanations to critically analyze retrieved passages, requiring significantly fewer training examples. arxiv.org/abs/2410.22874

Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task Leonardo Ranaldi et al. introduce a method that translates retrieved multilingual documents into a common language before generating responses. 📝arxiv.org/abs/2504.03616