← Search

Ashutosh Sharma

2 accepted papers

2024

DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines

ICLR 2024spotlight

The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipelines are typically implemented using hard-coded “prompt templates”, i.e. lengthy strings discovered via trial and error.…

2024

IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages

ACL 2024short

In this paper, we introduce Neural Information Retrieval resources for 11 widely spoken Indian Languages (Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, and Telugu) from two major Indian language families (Indo-Aryan and Dravidian). These resources include (a…