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…
📢 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: 28/10/26
sites.google.com/view/worksh…
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
🚀 SemEval-2026 Task 11 is now live!
Disentangling Content and Formal Reasoning in Language Models
We invite you to join our task exploring content-independent, multilingual logical reasoning.
Task website: sites.google.com/view/semeva…
#NLProc #LLM
1
1
84
📅 Dates
- CodaBench evaluation data release: 1 Dec 2025
- Practice: 10–31 Dec 2025
- Evaluation: 10–31 Jan 2026
- Paper submission: Feb 2026
- Notifications: March 2026
- SemEval Workshop, Summer 2026
🔗 Info & Task (sites.google.com/view/semeva…)
Slack: join.slack.com/t/semeval-202…
1
68
LLMs prioritise validation over facts, creating unsafe "sycophancy". Our X-Agent, uses reasoning to audit and correct this behaviour. It stops the model from blindly agreeing, ensuring interactions are safe, consistent, and factually grounded.
#NLProc
aclanthology.org/2025.emnlp-…
3
103
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.
Hey @jaseweston Take a look at our EMNLP work last year. It's not that far away! aclanthology.org/2024.emnlp-…
🤖Introducing: CoT-Self-Instruct 🤖
📝: arxiv.org/abs/2507.23751
- Builds high-quality synthetic data via reasoning CoT + quality filtering
- Gains on reasoning tasks: MATH500, AMC23, AIME24 & GPQA-💎
- Outperforms existing train data s1k & OpenMathReasoning
- Gains on non-reasoning tasks as well: AlpacaEval & ArenaHard
🧵1/3
1
251
Very excited to be here! @aclmeeting #ACL2025NLP #ACL2025
This morning presented our paper on Multimodal Multilingual Reasoning!
aclanthology.org/2025.acl-lo…
Many interesting interactions, feedback and new ideas for follow up!
Thank you guys @FedeRanaldi @Giuli12P2
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.
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 📚
Are you interested in the intersection of Mathematics and NLP?
Consider submitting your paper to #MathNLP 2025: The 3rd Workshop on Mathematical NLP. #EMNLP2025.
Submissions will open on June 25!
Take a look here for more details sites.google.com/view/mathnl…
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
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
Leonardo Ranaldi retweeted
#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…
Leonardo Ranaldi retweeted
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-…
Leonardo Ranaldi retweeted
Summary of Hinrich Schütze’s keynote at #EACL2024! Cannot agree on tough and exciting challenges!
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…
🚀🚀🚀
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-l…
See you in Malta!
@andrenfreitas @Idiap_ch
Leonardo Ranaldi retweeted
#Fairness and Instruction-following #LLMs : a test
P-AT @huggingface : huggingface.co/datasets/Huma…
P-AT @emnlpmeeting : aclanthology.org/2023.findin…
#NLProc #chatgpt4
w/ @esruzzetti @dariutso @Comment98 @l__ranaldi @znz8


















