Janis Goldzycher

PhD student in #NLProc at @cl_uzh focusing on hate speech, now over at 🦋

[Janis Goldzycher @jagoldz]

Check out MSTS, a new Multimodal Safety Test Suite for vision-language models! ⬇️ It has been so exciting to contribute to this project! ✨

[Paul Röttger @paul_rottger]

Today, we are releasing MSTS, a new Multimodal Safety Test Suite for vision-language models!

MSTS is exciting because it tests for safety risks *created by multimodality*. Each prompt consists of a text + image that *only in combination* reveal their full unsafe meaning.

🧵

[Paul Röttger @paul_rottger]

Today, we are releasing MSTS, a new Multimodal Safety Test Suite for vision-language models!

MSTS is exciting because it tests for safety risks *created by multimodality*. Each prompt consists of a text + image that *only in combination* reveal their full unsafe meaning.

🧵

[Manuel Tonneau @ManuelTonneau]

Can we detect #hatespeech at scale on social media?

To answer this, we introduce 🤬HateDay🗓️, a global hate speech dataset representative of a day on Twitter.

The answer: not really! Detection perf is low and overestimated by traditional eval methods

https://t.co/OznvktglzK
🧵

[Paul Röttger @paul_rottger]

This dataset by @ManuelTonneau is a game changer for ecological validity in hate speech research.

240k annotated posts that are multilingual, multicultural, and *actually representative* of one day on Twitter. Highly recommend checking out the paper for details 👇

[Agostina Calabrese 🦋 @agostina_cal]

I'm creating a 🦋 starter pack for researchers working on (fighting) online harms, if you would like to be added send along your username 🤓

🦋 https://t.co/2pP0JiDCKq

#NLProc #HateSpeech @WOAHWorkshop

[Pia Pachinger @PiaPachinger]

I will be talking about our paper on AustroTox, the first German language resource on topics related to toxicity containing span annotations, on Monday at the @aclmeeting findings poster session 1 (12:45-13:45). Come see me at the poster!

[Matteo Grigoletto @mattegrigoletto]

How can democracies counteract misinformation from autocracies? We analyze the EU's unprecedented ban on RT and Sputnik and find that it decreased the spread of pro-Russian propaganda on social media, but only shortly.

Excited to see our work on @voxeu ! https://t.co/iDB76mPhVz

[Workshop on Online Abuse and Harms @WOAHWorkshop]

🥁Outstanding paper of #WOAH2024🥁

🏆"The Uli Dataset: An Exercise in Experience Led Annotation of oGBV" by Arnav Arora et al.

Congrats to all the authors! 👏🏻

[Workshop on Online Abuse and Harms @WOAHWorkshop]

➡️Join us for the Poster Session! Come and see a variety of fascinating works!

For more details, visit: https://t.co/MwvxrKAFpF

#WOAH2024 #NAACL2024

[Polcom Vienna @polcom_vienna]

Interested in target-based offensive language detection of Austrian German? Published in Findings of the @aclmeeting 2024, @PiaPachinger & colleagues /@AMPlanitzer introduce the “AustroTox” dataset and evaluate fine-tuned and LLMs performance. Data & Code: https://t.co/1IqryWwhdR

[MilaNLP @MilaNLProc]

✨Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset: We introduce GAHD, a German adversarial hate speech dataset, and evaluate methods for efficiently collecting diverse, adversarial examples.

[Janis Goldzycher @jagoldz]

I‘ll be presenting this paper as a poster at #NAACL2024 today in an hour, from 11:00 to 12:30. Come by to discuss hatespeechXadversarial data collection!

[Janis Goldzycher @jagoldz]

New paper at #NAACL2024 🥳

We present GAHD, an 11k German Adversarial Hate speech Dataset 📜 and show that mixing annotator support strategies for finding adv. examples leads to a more effective dataset!

Great collab with @paul_rottger and @center_text!

Highlights below ⬇️

[MilaNLP @MilaNLProc]

👋Shout out to the @MilaNLProc crew at the conference! We have some awesome gifts waiting for you🎁
@donyarooein @CurriedAmanda @paul_rottger @jagoldz @florplaza22

[MilaNLP @MilaNLProc]

📜The @MilaNLProc lab is going to present 6 papers at #NAACL2024!

🧵Here's a tl;dr for each of them⤵️

#NLProc @naaclmeeting

[Janis Goldzycher @jagoldz]

@agostina_cal @Edin_CDT_NLP @EdinburghNLP @Snap Sounds very interesting, looking forward to the preprint!

[MilaNLP @MilaNLProc]

For this week's @MilaNLProc reading group, @jagoldz presented "Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations" by Zhuoyan Li et al.

Paper: https://t.co/stoCrstQOL

#NLProc #ReadingGroup

[Janis Goldzycher @jagoldz]

Can you trick our super-robust model trained on GAHD? 👀 https://t.co/b7jkl8CmPA
GAHD on GitHub: https://t.co/BnnMINLQzC
GAHD on 🤗: https://t.co/Eh0ZoMQJUA

[Janis Goldzycher @jagoldz]

New paper at #NAACL2024 🥳

We present GAHD, an 11k German Adversarial Hate speech Dataset 📜 and show that mixing annotator support strategies for finding adv. examples leads to a more effective dataset!

Great collab with @paul_rottger and @center_text!

Highlights below ⬇️

[Janis Goldzycher @jagoldz]

Check out the paper for additional details, such as an extensive error analysis and analyses of annotator disagreements: https://t.co/neileHox70