Nikhil Sharma ༗
@nikhilsksharma.bsky.social
CS PhD JohnsHopkins | Ex NLProc @ Genentech | Information Seeking | Disinformation Agents | Copilots for Social Good | PhD
@JHUCLSP @JHUMCEH
#NLProc
@JHUCLSP @JHUMCEH
#NLProc
Grateful for @wired.com 's coverage of our work on Generative Echo Chambers.
📰 Read the full article:
www.wired.it/article/chat...
📚 Explore our research:
🔗 aclanthology.org/2025.naacl-l...
🔗 dl.acm.org/doi/10.1145/...
#AI #LLMs #EchoChambers #ResponsibleAI #AIEthics
📰 Read the full article:
www.wired.it/article/chat...
📚 Explore our research:
🔗 aclanthology.org/2025.naacl-l...
🔗 dl.acm.org/doi/10.1145/...
#AI #LLMs #EchoChambers #ResponsibleAI #AIEthics
July 18, 2025 at 5:54 PM
Grateful for @wired.com 's coverage of our work on Generative Echo Chambers.
📰 Read the full article:
www.wired.it/article/chat...
📚 Explore our research:
🔗 aclanthology.org/2025.naacl-l...
🔗 dl.acm.org/doi/10.1145/...
#AI #LLMs #EchoChambers #ResponsibleAI #AIEthics
📰 Read the full article:
www.wired.it/article/chat...
📚 Explore our research:
🔗 aclanthology.org/2025.naacl-l...
🔗 dl.acm.org/doi/10.1145/...
#AI #LLMs #EchoChambers #ResponsibleAI #AIEthics
#NAACL2025 30 April - 2pm, Hall 3, Special Theme
"Faux Polyglots: A study on Information Disparity in Multilingual Large Language Models".
Come visit and learn about how multilingual RALMs fail to handle multilingual information conflicts.
Teaser: youtu.be/aPS2Ntav1FE
#LLM #AI #NLProc
"Faux Polyglots: A study on Information Disparity in Multilingual Large Language Models".
Come visit and learn about how multilingual RALMs fail to handle multilingual information conflicts.
Teaser: youtu.be/aPS2Ntav1FE
#LLM #AI #NLProc
Are multilingual LLMs ready for the challenges of real-world information-seeking where diverse perspectives and facts are represented in different languages?
Unfortunately, No.
We find LLMs are faux polyglots.
📢Preprint: tinyurl.com/fdunz3dz
#LLMs #NLProc
Unfortunately, No.
We find LLMs are faux polyglots.
📢Preprint: tinyurl.com/fdunz3dz
#LLMs #NLProc
April 28, 2025 at 2:46 PM
#NAACL2025 30 April - 2pm, Hall 3, Special Theme
"Faux Polyglots: A study on Information Disparity in Multilingual Large Language Models".
Come visit and learn about how multilingual RALMs fail to handle multilingual information conflicts.
Teaser: youtu.be/aPS2Ntav1FE
#LLM #AI #NLProc
"Faux Polyglots: A study on Information Disparity in Multilingual Large Language Models".
Come visit and learn about how multilingual RALMs fail to handle multilingual information conflicts.
Teaser: youtu.be/aPS2Ntav1FE
#LLM #AI #NLProc
Reposted by Nikhil Sharma ༗
🚨 You are only evaluating a slice of your test-time scaling model's performance! 🚨
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
February 20, 2025 at 3:14 PM
🚨 You are only evaluating a slice of your test-time scaling model's performance! 🚨
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
Thrilled that our paper Faux Polyglot has been accepted to #NAACL2025 main! 🚀
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models
With Retrieval Augmented Generation (RAG), Large Language Models (LLMs) are playing a pivotal role in information search and are being adopted globally. Although the multilingual capability of LLMs of...
arxiv.org
January 31, 2025 at 3:19 PM
Thrilled that our paper Faux Polyglot has been accepted to #NAACL2025 main! 🚀
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
We show that multilingual RAG creates language-specific information cocoons and amplifies perspectives and facts in the dominant language, especially when handling knowledge conflicts.
📜 arxiv.org/abs/2407.05502
Reposted by Nikhil Sharma ༗
Putting together a JHU Center for Language and Speech Processing starter pack!
Please reply or DM me if you're doing research at CLSP and would like to be added - I'm still trying to find out which of us are on here so far.
go.bsky.app/JtWKca2
Please reply or DM me if you're doing research at CLSP and would like to be added - I'm still trying to find out which of us are on here so far.
go.bsky.app/JtWKca2
CLSP
Join the conversation
go.bsky.app
November 19, 2024 at 3:37 PM
Putting together a JHU Center for Language and Speech Processing starter pack!
Please reply or DM me if you're doing research at CLSP and would like to be added - I'm still trying to find out which of us are on here so far.
go.bsky.app/JtWKca2
Please reply or DM me if you're doing research at CLSP and would like to be added - I'm still trying to find out which of us are on here so far.
go.bsky.app/JtWKca2
Had a good conversation about "What exactly is misinformation?" with
@williamjurayj.bsky.social
Thread below
@williamjurayj.bsky.social
Thread below
December 6, 2024 at 7:54 PM
Had a good conversation about "What exactly is misinformation?" with
@williamjurayj.bsky.social
Thread below
@williamjurayj.bsky.social
Thread below