6 citations · 6 across the 3 of their papers we have counts for
7 papers
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda +2
The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the…
Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization
Ahmed Magooda, Diane Litman
This paper explores three simple data manipulation techniques (synthesis, augmentation, curriculum) for improving abstractive summarization models without the need for any addition…
Exploring Multitask Learning for Low-Resource AbstractiveSummarization
Ahmed Magooda, Mohamed Elaraby, Diane Litman
This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different task…
Abstractive Summarization for Low Resource Data using Domain Transfer and Data Synthesis
Ahmed Magooda, Diane Litman
Training abstractive summarization models typically requires large amounts of data, which can be a limitation for many domains. In this paper we explore using domain transfer and d…
Attend to the beginning: A study on using bidirectional attention for extractive summarization
Ahmed Magooda, Cezary Marcjan
Forum discussion data differ in both structure and properties from generic form of textual data such as news. Henceforth, summarization techniques should, in turn, make use of such…