Leonardo Ranaldi

~ NLP Researcher ~ @EdinburghNLP

[Leonardo Ranaldi @l__ranaldi]

@fly51fly Really interesting! We have framed this process in sycophantic scenarios in the past https://t.co/m9nTW1JqdM

[eaclmeeting @eaclmeeting]

Do you need a weekend read? The proceedings of #EACL2026 and co-located workshops are now online!

https://t.co/v51o9GxgdR

#NLProc

[Leonardo Ranaldi @l__ranaldi]

📅 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 (https://t.co/3ffAvnhtBk)

Slack: https://t.co/lGdc3aPxHh

[Leonardo Ranaldi @l__ranaldi]

🚀 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: https://t.co/3ffAvngVLM

#NLProc #LLM

[Leonardo Ranaldi @l__ranaldi]

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

https://t.co/m9nTW1JY3k

[Leonardo Ranaldi @l__ranaldi]

@QuYuxiao Exciting! Check out our previous work which on symbolic abstraction https://t.co/Bviyp0d5mP

[Leonardo Ranaldi @l__ranaldi]

@iScienceLuvr They might think better, but what about sycophancy? RL doesn't seem like a good friend https://t.co/bka4BAEwz4

[Leonardo Ranaldi @l__ranaldi]

@jiqizhixin Exciting! I'm sharing our past work with you, which is actually in line with GTA https://t.co/uOUOKEk8Ay

[Leonardo Ranaldi @l__ranaldi]

@fly51fly Exiting work! Please take a look to this related https://t.co/y6Ui7x80jR

[Leonardo Ranaldi @l__ranaldi]

@wyu_nd @zli12321 @LiangZhenwen @FuxiaoL @haitaominlp @boydgraber @ChengsongH31219 Really exciting! I share with you our self-rewarding paper on multilingual VLM https://t.co/rXfamwLcrS

[Leonardo Ranaldi @l__ranaldi]

@fly51fly We are here too! https://t.co/rXfamwLcrS

[Leonardo Ranaldi @l__ranaldi]

@yuyinzhou_cs Really great work guys! We have done something similar in the multi-lingual modal context https://t.co/rXfamwLcrS

[Leonardo Ranaldi @l__ranaldi]

@fly51fly Exciting work! We did something related using RL + curriculum learning with really consistent improvements https://t.co/rXfamwLcrS

[Fede_Ranaldi @FedeRanaldi]

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.

[Leonardo Ranaldi @l__ranaldi]

Hey @jaseweston Take a look at our EMNLP work last year. It's not that far away! https://t.co/y6Ui7x80jR

[Jason Weston @jaseweston]

🤖Introducing: CoT-Self-Instruct 🤖
📝: https://t.co/OXFALvsDgh
- 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

[Leonardo Ranaldi @l__ranaldi]

@aclmeeting @HumanCentricArt #ACL2025 #ACL2025NLP #NLP #NLP

[Giulia Pucci @Giuli12P2]

💣💣This morning at #ACL2025, preventing these two brothers from fighting💣💣(they're R2, I am MultiOmnia, lol) #ACL2025NLP
#CompLing #Vienna
https://t.co/64pIYHRAff
@l__ranaldi @FedeRanaldi

[Leonardo Ranaldi @l__ranaldi]

Very excited to be here! @aclmeeting #ACL2025NLP #ACL2025

This morning presented our paper on Multimodal Multilingual Reasoning!
https://t.co/rXfamwLcrS

Many interesting interactions, feedback and new ideas for follow up!

Thank you guys @FedeRanaldi @Giuli12P2

[Fede_Ranaldi @FedeRanaldi]

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: https://t.co/PVKZdEqrdx

[ACL 2026 @aclmeeting]

📢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▶️https://t.co/w7YpPwTPPx
#NLProc #ACL2025NLP #ACLAnthology 📚

[Leonardo Ranaldi @l__ranaldi]

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 https://t.co/3CY7mYCwMR