5 papers
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty +2
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation…
Multilingual Language Models Encode Script Over Linguistic Structure
Aastha A K Verma, Anwoy Chatterjee, Mehak Gupta +1
Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal…
Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge
Eshaan Tanwar, Anwoy Chatterjee, Michael Saxon +3
Most multilingual question-answering benchmarks, while covering a diverse pool of languages, do not factor in regional diversity in the information they capture and tend to be West…
HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations
Anwoy Chatterjee, Yash Goel, Tanmoy Chakraborty
Contemporary Language Models (LMs), while impressively fluent, often generate content that is factually incorrect or unfaithful to the input context - a critical issue commonly ref…
POSIX: A Prompt Sensitivity Index For Large Language Models
Anwoy Chatterjee, H S V N S Kowndinya Renduchintala, Sumit Bhatia +1
Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in prompts, often generating significantly divergent…