← Search

Nabiha Asghar

2 accepted papers

2025

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting

NAACL 2025industry

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts need to be updated to re-optimize the task performance. We…

Cited by 0SourcePDFScholar
2020

Progressive Memory Banks for Incremental Domain Adaptation

ICLR 2020poster

This paper addresses the problem of incremental domain adaptation (IDA) in natural language processing (NLP). We assume each domain comes one after another, and that we could only access data in the current domain. The goal of IDA is to build a unified model performing well on all the domains that…

Cited by 32SourcecodeScholar