Thomas Palmeira
@thomaspalmeira.bsky.social
Working with #LLMs #NLP #Speech for Multilingual, Low-Resource, and Efficient ML
PhD Track at @Polytechnique and @TelecomParis. Science saves lifes! #EMNLP2024 #LoG2024 #NeurIPS2024
http://thomas-ferraz.github.io
https://linktr.ee/_thomaspf
PhD Track at @Polytechnique and @TelecomParis. Science saves lifes! #EMNLP2024 #LoG2024 #NeurIPS2024
http://thomas-ferraz.github.io
https://linktr.ee/_thomaspf
The result is that you often need to double or triple-check their responses to ensure accuracy because it’s easy to be convinced by an answer that sounds good at first glance but, in detail, makes no sense at all…
November 28, 2024 at 3:56 PM
The result is that you often need to double or triple-check their responses to ensure accuracy because it’s easy to be convinced by an answer that sounds good at first glance but, in detail, makes no sense at all…
However, the way this feedback is gathered and knowledge limitations of LLMs, has often led these models to learn how to seem useful and relevant, even when they are not.
November 28, 2024 at 3:56 PM
However, the way this feedback is gathered and knowledge limitations of LLMs, has often led these models to learn how to seem useful and relevant, even when they are not.
🚀 Don’t miss our #LoG2024 poster on Tue, Nov 28 @ 15:00 GMT!
Join us to discuss GNNs + LLMs for disinformation detection. The conference registration is free!
#FakeNewsDetection #GNNs #AI #LLMs @logconference.bsky.social
Join us to discuss GNNs + LLMs for disinformation detection. The conference registration is free!
#FakeNewsDetection #GNNs #AI #LLMs @logconference.bsky.social
November 28, 2024 at 1:52 PM
🚀 Don’t miss our #LoG2024 poster on Tue, Nov 28 @ 15:00 GMT!
Join us to discuss GNNs + LLMs for disinformation detection. The conference registration is free!
#FakeNewsDetection #GNNs #AI #LLMs @logconference.bsky.social
Join us to discuss GNNs + LLMs for disinformation detection. The conference registration is free!
#FakeNewsDetection #GNNs #AI #LLMs @logconference.bsky.social
🙌 Collaborators:
This research is part of @BrunoCroso’s undergrad internship at POLI-USP at @roseli_deus lab.
📄 Paper: arxiv.org/pdf/2410.19193
📂 Code: github.com/BrunoCroso/C...
📜 More details: linktr.ee/_thomaspf
This research is part of @BrunoCroso’s undergrad internship at POLI-USP at @roseli_deus lab.
📄 Paper: arxiv.org/pdf/2410.19193
📂 Code: github.com/BrunoCroso/C...
📜 More details: linktr.ee/_thomaspf
https://github.com/BrunoCroso/Con…
November 28, 2024 at 1:50 PM
🙌 Collaborators:
This research is part of @BrunoCroso’s undergrad internship at POLI-USP at @roseli_deus lab.
📄 Paper: arxiv.org/pdf/2410.19193
📂 Code: github.com/BrunoCroso/C...
📜 More details: linktr.ee/_thomaspf
This research is part of @BrunoCroso’s undergrad internship at POLI-USP at @roseli_deus lab.
📄 Paper: arxiv.org/pdf/2410.19193
📂 Code: github.com/BrunoCroso/C...
📜 More details: linktr.ee/_thomaspf
📊 Key findings:
1️⃣ Contextual text representations (BERTweet) improve Macro F1 by 33.8% over GNNs without text.
2️⃣ Retweets provide richer signals than user bios, but combined reach the best result.
3️⃣ Noise injection augmentation (commonly used in LLMs) reduces training stability.
1️⃣ Contextual text representations (BERTweet) improve Macro F1 by 33.8% over GNNs without text.
2️⃣ Retweets provide richer signals than user bios, but combined reach the best result.
3️⃣ Noise injection augmentation (commonly used in LLMs) reduces training stability.
November 28, 2024 at 1:49 PM
📊 Key findings:
1️⃣ Contextual text representations (BERTweet) improve Macro F1 by 33.8% over GNNs without text.
2️⃣ Retweets provide richer signals than user bios, but combined reach the best result.
3️⃣ Noise injection augmentation (commonly used in LLMs) reduces training stability.
1️⃣ Contextual text representations (BERTweet) improve Macro F1 by 33.8% over GNNs without text.
2️⃣ Retweets provide richer signals than user bios, but combined reach the best result.
3️⃣ Noise injection augmentation (commonly used in LLMs) reduces training stability.
📰 Why?
We know disinformation campaigns erode public trust on information.
On the technical side, few works leverage Transformers/LLMs advances to encode information in GNNs. Our work explore using contextual representations (from user bios & replies) to enhance fake news detection.
We know disinformation campaigns erode public trust on information.
On the technical side, few works leverage Transformers/LLMs advances to encode information in GNNs. Our work explore using contextual representations (from user bios & replies) to enhance fake news detection.
November 28, 2024 at 1:48 PM
📰 Why?
We know disinformation campaigns erode public trust on information.
On the technical side, few works leverage Transformers/LLMs advances to encode information in GNNs. Our work explore using contextual representations (from user bios & replies) to enhance fake news detection.
We know disinformation campaigns erode public trust on information.
On the technical side, few works leverage Transformers/LLMs advances to encode information in GNNs. Our work explore using contextual representations (from user bios & replies) to enhance fake news detection.
Photo with some of my amazing co-authors!
November 25, 2024 at 4:32 PM
Photo with some of my amazing co-authors!