Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs
Parsa Hejabi, Elnaz Rahmati, Alireza S. Ziabari +1
Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt. In this paper, we propose Flip-Flop Consistency (), an…
cs.CL2024
Cost-Efficient Subjective Task Annotation and Modeling through Few-Shot Annotator Adaptation
Preni Golazizian, Alireza S. Ziabari, Ali Omrani +1
In subjective NLP tasks, where a single ground truth does not exist, the inclusion of diverse annotators becomes crucial as their unique perspectives significantly influence the an…
cs.CL2023
Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning
Ali Omrani, Alireza S. Ziabari, Preni Golazizian +2
Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving la…