Leonardo Ranaldi (@l__ranaldi) profile picture

~ NLP Researcher ~ @EdinburghNLP

Joined March 2022
Photo by Leonardo Ranaldi (@l__ranaldi)
Leonardo Ranaldi retweeted
📢 Call for Papers: ORACLE – EMNLP 2026! 🇭🇺 Are #LLMs truly global oracles? Translation is sorted, but what about reasoning? Can our models think and act across different cultures and languages? 🔮 📅 Dates Deadline: 1/8/26 Workshop day: 28/10 Website: sites.google.com/view/worksh…
1
1
1
205
Leonardo Ranaldi retweeted
Do you need a weekend read? The proceedings of #EACL2026 and co-located workshops are now online! aclanthology.org/events/eacl… #NLProc
6
20
1,822
Leonardo Ranaldi retweeted
I propose the concept of #protoknowledge (in-between #memorization and #generalization) to evaluate whether models are truly capable of solving downstream tasks. Thanks to the @l2m2_workshop part of @aclmeeting , I could receive valuable feedback and engage idea exchanges.
4
8
62
5,052
Leonardo Ranaldi retweeted
I will be at #ACL2025 with my group presenting 3 Conference Papers. At the #L2M2 workshop, we will introduce the concept of #protoknowledge as a framework for jointly analyzing the #memorization and #generalization capabilities of LLMs. Link Non-archival: lnkd.in/deDqJAxM
Privacy, Memorization, Multimodal reasoning, and the surge of protoknowledge (non-archival in L2M2 Workshop) ! This is our contribution to #ACL2025NLP to better understand #LLMs We want to know your POV! See you in Vienna! We are hiring.
1
1
5
260
Leonardo Ranaldi retweeted
📢The ACL 2025 Proceedings are LIVE🎆on the ACL Anthology! 🎉 We're thrilled to pre-celebrate the incredible research that will be presented starting Monday, July 28th, in Vienna! 🇦🇹 Start exploring now▶️aclanthology.org/events/acl-… #NLProc #ACL2025NLP #ACLAnthology 📚
2
23
2
89
7,449
Leonardo Ranaldi retweeted
Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task @l__ranaldi et al. introduce a method that translates retrieved multilingual documents into a common language before generating responses. 📝arxiv.org/abs/2504.03616
1
2
251
Leonardo Ranaldi retweeted
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
7
26
2,250
#UnboxingTransformer If you are in #ACL2024NLP #ACL2024, we are sure: 1) you can try to solve our challenge uniroma2-my.sharepoint.com/:… 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/f4-2…
7
8
647
At last, a curriculum learning that works, one for pretraining and another for instruction tuning @l__ranaldi @Giuli12P2 @andrenfreitas @znz8 aclanthology.org/2024.lrec-m… aclanthology.org/2023.ranlp-…
2
15
4
75
12,322
Leonardo Ranaldi retweeted
Summary of Hinrich Schütze’s keynote at #EACL2024! Cannot agree on tough and exciting challenges!
1
5
1
25
2,658
Leonardo Ranaldi retweeted
Waiting for @l__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-l… 🚀🚀🚀
1
2
12
630
It's nearly #Xmas2023 #LLM s and #ChatGPT should become better persons with less #BIAS Let's measure it! The paper : aclanthology.org/2023.findin… The dataset : huggingface.co/datasets/Huma… #NLProc at #EMNLP2023 @esruzzetti @dariutso @Comment98 @l__ranaldi @znz8
3
1
312
#EMNLP2023 challenge Tag a paper you see with #PsycoanalysisOfLLMs if you think it is
5
7
364
Hey, @AILC_NLP, we are arriving disentraining in a few minutes! #clicit2023 #NLProc @esruzzetti @DarioOnorati @leonardoranaldi @Ranaldinho99 @Giuli12P2 and Davide Venditti Eager to learn from and to network with #clicit2023's participants!
4
7
252
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 @unitorvergata has a new X accout
3
1
9
880
#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.pdf
2
4
177