Chahat Raj

CS Ph.D. Candidate @GeorgeMasonU NLP || Ethics || Society & Culture || Cognitive Sciences

[Chahat Raj @chahatsaidit]

#ACL2026 has been eventful ✨

Presented Vignette as an Oral and had amazing conversations over Talent or Luck in the poster session.

Also received an SAC Highlight award for Vignette 🫶🏼

@ZzwWilliam @anas_ant @aylin_cim @iamshnoo
#NLProc @aclmeeting #ACL2026NLP

[Chahat Raj @chahatsaidit]

Also presenting Talent or Luck at 2:00 PM today, Grand Hall, G43!

Come to see how socio-psychological interpretations influence LLM outputs 👀

https://t.co/c1oDUHuWul

@ZzwWilliam, @anas_ant, @aylin_cim

#ACL2026

[Chahat Raj @chahatsaidit]

Excited to present Vignette at #ACL2026!

Come stop by Promenade during Oral Session A (11:00-12:30) to hear about our work on evaluating social bias in vision-language models.

With amazing co-authors @ZzwWilliam, @anas_ant, @aylin_cim

Paper: https://t.co/hK8hod9net

[Chahat Raj @chahatsaidit]

I’m in San Diego to attend #ACL2026. I’ll be presenting two papers on Sunday, July 5th, an oral and a poster session.

See you there!

[Chahat Raj @chahatsaidit]

#MASCSLL2025 was fun! @penn_state has been a great host ♥️ Loved the conversations I had with all of those who stopped by my posters :)

[Chahat Raj @chahatsaidit]

EMNLP is always fun! #EMNLP2024 @emnlpmeeting
@anas_ant @iamshnoo @ZzwWilliam

[Antonis Anastasopoulos @anas_ant]

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

[Chahat Raj @chahatsaidit]

I'll be at #EMNLP2024 with @iamshnoo presenting BiasDora. Catch us on Thursday, Nov 14, Session 11. @aylin_cim @anas_ant @ZzwWilliam @emnlpmeeting

[Chahat Raj @chahatsaidit]

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: https://t.co/3qYn6YWNHP, explores them all! 🧵

[Chahat Raj @chahatsaidit]

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 https://t.co/SlRkIkTvGq
@anas_ant @ZzwWilliam

[Alex Choi @alex_choi_cs]

🧑🤖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 explores both the potential benefits and worrisome pitfalls of this emerging partnership.

📜Preprint available: https://t.co/bq7qYCIUZ6

w/ @SyedaSabrina11, @Prof_JPSingh, and @anas_ant

1/6

[Chahat Raj @chahatsaidit]

(5/n) Grateful to my wonderful advisors and collaborators @iamshnoo, @aylin_cim, @anas_ant, and @ZzwWilliam 😇

[Chahat Raj @chahatsaidit]

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: https://t.co/3qYn6YWNHP, explores them all! 🧵

[Chahat Raj @chahatsaidit]

(4/n) GPT-4o and LLaMA-3 text completions reveal strong toxicity toward sexuality and disability. Stable Diffusion shows age and gender biases, while DALL-E 3 displays disability stereotypes in image generations. Disability bias is a standout issue in image descriptions as well for both GPT-4o and LLaVA.

[Chahat Raj @chahatsaidit]

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: https://t.co/76HQdzuVb0

[Chahat Raj @chahatsaidit]

Do language models reflect human biases across languages and cultures? Had a fun time presenting at @emnlpmeeting with @iamshnoo

We handed out stickers to those who came by!

[Chahat Raj @chahatsaidit]

RT @iamshnoo: Got my first paper during PhD accepted into the main conference for #EMNLP2023 @emnlpmeeting ! Very grateful for my amazing c…

[Francesca Rossi @frossi_t]

Great crowd at AIES 2023!
#aies2023 #aiethics #responsibleai

[Anjishnu @iamshnoo]

GMU students with Hugging Face 🤗

@ClementDelangue @huggingface
#DCAINight