Ishika Agarwal
@wonderingishika.bsky.social
CS PhD @ UIUC | Data Efficiency NLP | Conversational AI | agarwalishika.github.io | same handle on twitter
Pinned
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.
We tackle expensive fine-tuning by selecting a small subset of informative data that targets a model's weaknesses.
🚀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!
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!
February 17, 2025 at 4:06 AM
🚀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!
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!
Elated to announce that DELIFT has been accepted to ICLR'25 🎉 Looking forward to discussing it in Singapore!
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.
We tackle expensive fine-tuning by selecting a small subset of informative data that targets a model's weaknesses.
January 23, 2025 at 3:46 PM
Elated to announce that DELIFT has been accepted to ICLR'25 🎉 Looking forward to discussing it in Singapore!
Reposted by Ishika Agarwal
Congratulations to @dilekh.bsky.social for her ACL Fellowship! 🎉🎉🎉 www.aclweb.org/portal/conte...
ACL Fellows 2024 | ACL Member Portal
www.aclweb.org
December 11, 2024 at 2:35 PM
Congratulations to @dilekh.bsky.social for her ACL Fellowship! 🎉🎉🎉 www.aclweb.org/portal/conte...
Reposted by Ishika Agarwal
The last response from Gemini in this thread may shock you: gemini.google.com/share/6d141b...
Gemini - Challenges and Solutions for Aging Adults
Created with Gemini
gemini.google.com
November 24, 2024 at 7:28 AM
The last response from Gemini in this thread may shock you: gemini.google.com/share/6d141b...
Reposted by Ishika Agarwal
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!
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!
November 19, 2024 at 5:23 PM
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!
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!
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
(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
Bluesky academics, lets get to know each other! Quote this & tell me: 1) a project you are working on & 2) an odd idea/theory you aren’t working on but keep thinking about
1. I came to hate my work and thinking so don't do it anymore.
2.
1. I came to hate my work and thinking so don't do it anymore.
2.
Bluesky academics, lets get to know each other! Quote this & tell me: 1) a project you are working on & 2) an odd idea/theory you aren’t working on but keep thinking about
1. Convincing everyone that everything is luck, all the way down.
2. LLM’s can reason and understand in the external sense.
1. Convincing everyone that everything is luck, all the way down.
2. LLM’s can reason and understand in the external sense.
November 17, 2024 at 11:46 PM
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
(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
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.
We tackle expensive fine-tuning by selecting a small subset of informative data that targets a model's weaknesses.
November 17, 2024 at 7:27 PM
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.
We tackle expensive fine-tuning by selecting a small subset of informative data that targets a model's weaknesses.
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!
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!
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...
arxiv.org
November 17, 2024 at 7:24 PM
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!
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!