iiinova — where your digital self keeps evolving

Ishika Agarwal

@wonderingishika.bsky.social

905 followers 396 following 22 posts

CS PhD @ UIUC | Data Efficiency NLP | Conversational AI | agarwalishika.github.io | same handle on twitter

Posts Replies Media

Ishika Agarwal @wonderingishika.bsky.social · 17/02/2025

🚀Very excited about my new paper! NN-CIFT slashes data valuation costs by 99% using tiny neural nets (205k params, just 0.0027% of 8B LLMs) while maintaining top-tier performance!

1114

Ishika Agarwal @wonderingishika.bsky.social · 23/01/2025

Elated to announce that DELIFT has been accepted to ICLR'25 🎉 Looking forward to discussing it in Singapore!

030

Reposted by Ishika Agarwal

ConvAI @ UIUC @convai-uiuc.bsky.social · 11/12/2024

Congratulations to @dilekh.bsky.social for her ACL Fellowship! 🎉🎉🎉 www.aclweb.org/portal/conte...

aclweb.org

ACL Fellows 2024 | ACL Member Portal

0112

Reposted by Ishika Agarwal

Manoj Agarwal @agarwalmk.bsky.social · 24/11/2024

The last response from Gemini in this thread may shock you: gemini.google.com/share/6d141b...

gemini.google.com

‎Gemini - Challenges and Solutions for Aging Adults

Created with Gemini

191

Reposted by Ishika Agarwal

Priyanka Kargupta @ EMNLP'24 @pkargupta.bsky.social · 19/11/2024

Can LLMs make us critical thinkers? TreeInstruct reorients assistant-like LLMs to be instructors that guide students towards understanding their mistakes, without providing direct/indirect answers. Check out aclanthology.org/2024.finding... (w/ @wonderingishika.bsky.social) to learn more!

121

Ishika Agarwal @wonderingishika.bsky.social · 17/11/2024

All around the theme of data-efficient NLP: (1) using influence functions to improve language model performance from less data (2) enabling language models to generate queries for things it doesn't know

030

Ishika Agarwal @wonderingishika.bsky.social · 17/11/2024

I'm so excited to share my latest paper called DELIFT along with Krishnateja Killamsetty, Lucian Popa, and Marina Danilevksy at IBM Research 🎉 We tackle expensive fine-tuning by selecting a small subset of informative data that targets a model's weaknesses.

291

Ishika Agarwal @wonderingishika.bsky.social · 17/11/2024

Can LLMs make us critical thinkers? TreeInstruct reorients LLMs to be instructors that guide students socratically to solve problems, instead of assistants that provide direct answers. Check out our EMNLP2024 paper at arxiv.org/abs/2406.11709 (w/ @pkargupta.bsky.social) to learn more!

arxiv.org

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging

Socratic questioning is an effective teaching strategy, encouraging critical thinking and problem-solving. The conversational capabilities of large language models (LLMs) show great potential for prov...

120