Stefan Bejgu

[Babelscape @babelscape]

Four of our industrial #PhD students, @SBejgu, @PereLluisHC, @alescire94 and @SimoneTedeschi_, were awarded their #PhD in #AI last Friday with the best grades (and two cum laude)! Congrats all! 👏 🎉 With @RNavigli, their advisor and Babelscape's scientific director, in the photo

[Stefan Bejgu @SBejgu]

@rohanpaul_ai Thank you for highlighting our work! 🙌

You can explore the training and evaluation datasets on Hugging Face here: https://t.co/cuitPI7SGl.

[Rohan Paul @rohanpaul_ai]

Want to know if an AI is lying? LLM-OASIS helps detect factual accuracy in AI outputs with 81k training examples.

LLM-OASIS introduces the largest dataset for training factuality evaluators, created by extracting and falsifying information from Wikipedia articles. This enables end-to-end verification of AI-generated text accuracy.

-----

🤔 Original Problem:

LLMs still produce hallucinations in their outputs. Existing factuality evaluation resources are limited by being task-specific, small in size, or focused only on simple claim verification.

-----

🔧 Solution in this Paper:

→ LLM-OASIS extracts claims from Wikipedia passages using an LLM-based pipeline.

→ The system falsifies selected claims by introducing subtle but critical factual errors.

→ It generates pairs of factual and unfactual texts based on the original and modified claims.

→ The dataset covers 81k Wikipedia pages with 681k claims for training factuality evaluators.

-----

💡 Key Insights:

→ Task-agnostic factuality evaluation is possible with a large-scale synthetic dataset

→ Wikipedia provides reliable source material for generating factual/unfactual pairs

→ Human validation confirms high quality of automated data generation (90%+ accuracy)

-----

📊 Results:

→ GPT-4 achieves 60% accuracy on end-to-end factuality evaluation

→ 68% accuracy with Retrieval Augmented Generation

→ Human validation shows 96.78% accuracy for claim extraction

→ Dataset creation pipeline maintains 89-98% accuracy across all steps

[Valentino Maiorca @ValeMaiorca]

✨ Meet #ResiDual, a novel perspective on the alignment of multimodal latent spaces!

Think of it as a spectral "panning for gold" along the residual stream. It improves text-image alignment by simply amplifying task-related directions! 🌌🔍

https://t.co/UuXoYBBsT5

[1/6]

[Babelscape @babelscape]

🚀 Today marks the start of the @MakerFaireRome 🎉
We’re super excited to be part of it and introduce #Vera, our new LLM-powered fact-checking tool! 🤖🧠
Here’s a sneak peek of what you can expect at our booth! 👀✨
#MakerFaireRome #FactChecking #LLM #ArtificialIntelligence

[Babelscape @babelscape]

✨Tired of verifying #AI-generated info?😵
🔎Meet Vera, our #LLM-based fact-checker using trusted sources from the Web or your knowledge base.
💥Check out the live demo at Rome #MakerFaire2024 (Oct 25-27)!
More info 👉: https://t.co/OxrZ63rIbK
#FactChecking #Misinformation

[UniReps @unireps]

🔵🔴When do distinct learning processes learn similar representations?

Detecting patterns and conditions for this to happen is an open direction: a thread🧵

Working on this topic? Submit at: https://t.co/TjAbJcpAFk

DEADLINE: 20 Sept

See you at @NeurIPSConf! 🔵🔴

[1/N]

[SapienzaNLP @SapienzaNLP]

Post #ACL2024nlp dinner in #Bangkok with most of the presenting/attending band from our group + @Babelscape. Left to right: @SBejgu @LorenzoProiet13 @giumartinelli_ @19Stefano97 @RiccardoRicOrl @FMTucci @RNavigli @KarimAsh14 & Celebrating our outstanding paper award! #NLProc

[Francesco Maria Molfese @framolfese]

Come to chat with us at the poster session C in #EACL2024, starting now in room Radisson! #NLProc

[Alessandro Scirè @alescire94]

Exciting strides in text summarization with LLMs 🚀but verifying their factual accuracy is still an open challenge 🤔 We introduce FENICE, a factuality-oriented metric for summarization with a strong focus on interpretability🔍https://t.co/jjEI6lbxzG
#NLProc #LLMs #Factuality

[Francesco Maria Molfese @framolfese]

📢Happy to share that "Neuralign: A Context-Aware, Cross-Lingual and Fully-Neural Sentence Alignment System for Long Texts" has been accepted to #EACL2024 (main)

🫂Huge thanks to my co-authors @SBejgu @SimoneTedeschi_ @ConiaSimone @RNavigli

📃More details coming soon! #NLProc

[Simone Tedeschi @SimoneTedeschi_]

How to Mitigate Hallucinations in Large Language Models (#LLMs)?🤔

In this new @Medium article, I review the most recent research on mitigating hallucinations, and explain the main methods that are used to address this issue.

📑 https://t.co/R5c8JViYbg

#AI #NLP #GPT4 #LLM

[Babelscape @babelscape]

Tomorow at 5pm @SBejgu will present our research work on word alignment in 14 language pairs! @CLiC_it_conf #CliCit2023, joint with @SapienzaNLP and many other partners! #NLProc #LLMs

[Babelscape @babelscape]

Excited about #ChatGPT for your business?
Check out #Emotionary! The revolutionary #multilingual AI system that understands #emotions: #analyze customer reviews, #track feelings in #news, #socialmedia & #chatbot conversations!

https://t.co/HMIF4MRwYv

[Valentino Maiorca @ValeMaiorca]

📢 It looks like relative representations are here to stay!

I'm beyond thrilled to announce that our work has been selected as one of the notable top 5% (oral) papers at #iclr23 ! 🥳

https://t.co/nlZBiaIMHZ

[1/5]

[Roberto Navigli @RNavigli]

The Rome Workshop on 10 Years of #BabelNet & Multilingual Neurosymbolic Natural Language Understanding was a great success, with productive in-person discussions, amazing talks & >100 online participants! Thanks!
@ERC_Research @Babelscape @SapienzaNLP @SapienzaRoma @WikiResearch

[SapienzaNLP @SapienzaNLP]

Open & commercial Neural Machine Translation models heavily suffer from disambiguation biases! We present DiBiMT, our novel benchmark for lexical-semantic bias in MT at #ACL2022! By @Valahaar @FedeMartelli25 @FrancescoSaina @RNavigli
@ELEXIS_EU #NLProc

📝:https://t.co/8A8TN1DABj

[Babelscape @babelscape]

Empower your natural language applications with WordAtlas!
#WordAtlas is the next-generation multilingual knowledge graph. What makes it special is its linkage between words and concepts in hundreds of languages.
https://t.co/hIWZaCB6EP

[Turing Post @TheTuringPost]

Classy is a @PyTorch-based library for the fast prototyping and sharing of deep neural network models.

It wraps the best libraries like PyTorch Lightning, Transformers, @streamlit and offers them to users with a simple CLI interface.

Try it here: https://t.co/BM6nXI1aUc