Natural Language Processing

POSIX: Prompt Sensitivity Index for Large Language Models
Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in …
PDF Cite Poster Video DOI
SMART: Submodular Data Mixture Strategy for Instruction Tuning
Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the …
PDF Cite Poster Video DOI
INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models
A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and …
PDF Cite Poster Video DOI
Synthesizing Human Gaze Feedback for Improved NLP Performance
Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either …
PDF Cite Video DOI
Synthesizing Human Gaze Feedback for Improved NLP Performance