
Abhilasha Ravichander
@lasha_nlp
Postdoc @uwnlp working on Natural Language Processing (#NLProc) | PhD @SCSatCMU @LTIatCMU | ✨ On the academic job market ✨| primarily on 🦋
ID: 1940366048
https://lasharavichander.github.io/ 06-10-2013 09:14:07
861 Tweet
3,3K Followers
1,1K Following

We are launching HALoGEN💡, a way to systematically study *when* and *why* LLMs still hallucinate. New work w/ Shrusti Ghela* David Wadden Yejin Choi 💫 🧵 [1/n]
![Abhilasha Ravichander (@lasha_nlp) on Twitter photo We are launching HALoGEN💡, a way to systematically study *when* and *why* LLMs still hallucinate.
New work w/ <a href="/shrusti_ghela/">Shrusti Ghela</a>* <a href="/davidjwadden/">David Wadden</a> <a href="/YejinChoinka/">Yejin Choi</a> 💫
🧵 [1/n] We are launching HALoGEN💡, a way to systematically study *when* and *why* LLMs still hallucinate.
New work w/ <a href="/shrusti_ghela/">Shrusti Ghela</a>* <a href="/davidjwadden/">David Wadden</a> <a href="/YejinChoinka/">Yejin Choi</a> 💫
🧵 [1/n]](https://pbs.twimg.com/media/GimvuBZbYAYyXqP.jpg)




I'll be presenting two papers NAACL HLT 2025! 1. Why LLMs can't write a question with the answer "468" 🤔🙅 2. A multi-agent LLM that balances opinions on "is pineapple good on pizza?" 🎭🍕 Let's also chat about: 📍 Helpfulness 📍 Why MCQA sucks 📍 Generating cute paper titles 👀









