Papers by Mahmoud Aly
LexAbSumm: Aspect-based Summarization of Legal Decisions (2024.lrec-main)
Copied to clipboard
| Challenge: | LexAbSumm is a dataset designed for aspect-based summarization of legal documents . it is based on a set of ECtHR fact sheets, and is available for download. |
| Approach: | They propose a dataset designed for aspect-based summarization of legal case decisions . they evaluate abstractive summarizing models tailored for longer documents . |
| Outcome: | The proposed dataset is designed for aspect-based summarization of legal cases . it reveals a challenge in conditioning models to produce aspect-specific summaries . |
LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law (2025.acl-industry)
Copied to clipboard
| Challenge: | Recent efforts focus on automatic summarization of individual cases, which condense the content of a single case, making it easier for legal professionals to grasp key points. |
| Approach: | They propose a pipeline to generate multi-case structured reports using entire body of case law on user-specified topics within the European Court of Human Rights. |
| Outcome: | The proposed pipeline generates structured reports that enhance efficient, scalable legal analysis. |
Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language models (LLMs) are trained on vast amounts of data, including sensitive information that poses a risk to personal privacy if exposed. |
| Approach: | They propose a novel unlearning approach that utilizes an efficient reinforcement learning feedback loop via proximal policy optimization to incentivize the LLMs to learn a paraphrasing policy to unlearn the pre-training data. |
| Outcome: | The proposed approach surpasses strong baselines and state-of-the-art methods in terms of its ability to generalize and strike a balance between privacy and LLM performance. |
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding (2024.acl-long)
Copied to clipboard
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed Aly, Beidi Chen, Carole-Jean Wu
| Challenge: | Large Language Models (LLMs) have been deployed to many applications, yet their high compute and memory requirements lead to high financial and energy costs when deployed to GPU servers. |
| Approach: | They propose an end-to-end solution to speed-up inference of large language models . they apply layer dropout, and show that it increases the accuracy of early exit at earlier layers without adding any auxiliary layers or modules to the model. |
| Outcome: | The proposed method shows speedups of up to 2.16x on summarization for CNN/DM documents, 1.82x on coding, and 2.0x on TOPv2 semantic parsing task. |