5 papers
Are Multilingual Models Actually Improving? Isolating True Cross-Lingual Transfer
Prasoon Bajpai, Eleftheria Briakou, Colin Cherry +2
Cross-lingual transfer is a model's ability to generalize capabilities from well-represented source languages to under-represented target languages. Existing measures of a model's…
Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
Neha Kalibhat, Zi Wang, Prasoon Bajpai +4
We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior,…
Multilingual Test-Time Scaling via Initial Thought Transfer
Prasoon Bajpai, Tanmoy Chakraborty
Test-time scaling has emerged as a widely adopted inference-time strategy for boosting reasoning performance. However, its effectiveness has been studied almost exclusively in Engl…
Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks
Amey Hengle, Prasoon Bajpai, Soham Dan +1
Existing multilingual long-context benchmarks, often based on the popular needle-in-a-haystack test, primarily evaluate a model's ability to locate specific information buried with…
Information Anxiety in Large Language Models
Prasoon Bajpai, Sarah Masud, Tanmoy Chakraborty
Large Language Models (LLMs) have demonstrated strong performance as knowledge repositories, enabling models to understand user queries and generate accurate and context-aware resp…