Anjishnu
@iamshnoo
PhD student @GeorgeMasonU, 2x intern @Amazon, multimodal LLMs, understanding culture and fairness for NLP. Kpop, video games, dogs, cars. He/him
🎉 Our paper "Global Voices, Local Biases: Socio-Cultural Prejudices across Languages" has been accepted at #emnlp2023 ! Thread 🧵⬇️ 📜 arXiv : arxiv.org/pdf/2310.17586… 🤗 dataset : huggingface.co/datasets/iamsh… (@huggingface) 🕸️ website : iamshnoo.github.io/global_voices_…

Presenting this at #WACV2025 today + oral session tomorrow. Come say hi if you are around!
🧵1/ New Paper! 🚀 Our latest work with @anas_ant and @ZzwWilliam is now on arXiv. arxiv.org/pdf/2407.02067! We look at cultural understanding in LLMs and develop an approach for automatically updating the culture represented in images. Thread 🧵⬇️
Stop by Jasmine #20 right now to see how @iamshnoo and @chahatsaidit explore multimodal LLMs to uncover the implicit associations they make in their BiasDora work
I'll be at #EMNLP2024 with @iamshnoo presenting BiasDora. Catch us on Thursday, Nov 14, Session 11. @aylin_cim @anas_ant @ZzwWilliam @emnlpmeeting
We have seen the usual man:doctor🧑⚕️ and woman:nurse👩⚕️ stereotypes. But guess what? VLMs are also throwing out wild associations like blonde:dumb🤦♀️, old person:dinosaur🦕, or college student:broke. 🧑🎓💸 BiasDora, our #EMNLP2024 Findings Paper: arxiv.org/pdf/2407.02066, explores…
I'll be at @AIESConf with @aylin_cim and @iamshnoo to show how LLM responses imitate human psychology and how we use it to mitigate social bias using the Contact Hypothesis. Listen to our talk on Wednesday, Oct 23rd, when we present bit.ly/BreakingBiasBu… @anas_ant @ZzwWilliam
🧑🤖The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead❓ This is obviously a massive question that is both important and timely. Accepted to #EMNLP2024 Main, our paper examines the integration of LLMs into specialized expert workflows, and…
We have seen the usual man:doctor🧑⚕️ and woman:nurse👩⚕️ stereotypes. But guess what? VLMs are also throwing out wild associations like blonde:dumb🤦♀️, old person:dinosaur🦕, or college student:broke. 🧑🎓💸 BiasDora, our #EMNLP2024 Findings Paper: arxiv.org/pdf/2407.02066, explores…
I am in NAACL this week. Presenting my work on scaling up multilingual news framing analysis (through crowdsourcing) and how do LLMs perform on these tasks. In Person Presentation: June 19 11:00 AM - June 19 12:30 PM Poster Session 7 LOCATION: DON DIEGO 2, 3 & 4 @anas_ant
Presented our work @ecir2024 in Glasgow! #SALSA 💃 Leveraging salience scores for crafting interpretable adversarial attacks in fake news detection models. Exciting discussions on enhancing AI robustness, (also ethics, fairness and biases)! Paper: dx.doi.org/10.1007/978-3-…
Talked about human biases in language models and how they vary across languages with @chahatsaidit @anas_ant at EMNLP 2023!

