Author

Prasoon Bajpai

Observed name: Bajpai, Prasoon

Institution: Indian Institute of Technology Delhi

Observed institution: Indian Institute of Technology Delhi

OpenAlex ID: A5107956331

Are Multilingual Models Actually Improving? Isolating True Cross-Lingual Transfer

2026 · Bajpai, Prasoon, Briakou, Eleftheria, et al. · arXiv (Cornell University)

Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval over haystacks

2026 · Association for Computational Linguistics 2026, Bajpai, Prasoon, et al. · Underline Science Inc.

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

2026 · Kalibhat, Neha, Wang, Zi, et al. · arXiv (Cornell University)

Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval over haystacks

2026 · Amey Hengle, Prasoon Bajpai, et al. · Conference of the European Chapter of the Association for Computational Linguistics

Multilingual Test-Time Scaling via Initial Thought Transfer

2025 · Bajpai, Prasoon, Chakraborty, Tanmoy · arXiv (Cornell University)

Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks

2025 · Hengle, Amey, Bajpai, Prasoon, et al. · arXiv (Cornell University)

Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models

2025 · Amey Hengle, Prasoon Bajpai, et al. · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)

Information Anxiety in Large Language Models

2024 · Bajpai, Prasoon, Masud, Sarah, et al. · arXiv (Cornell University)

Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models

2024 · Hengle, Amey, Bajpai, Prasoon, et al. · arXiv (Cornell University)

Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators

2024 · Prasoon Bajpai, Niladri Chatterjee, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 12

Citation count:

H-index:

I10-index: