Sahel Sharifymoghaddam

@inproceedings{sharifymoghaddam2025rank,
title={RankLLM: A Python Package for Reranking with LLMs},
author={Sharifymoghaddam, Sahel and Pradeep, Ronak and Slavescu, Andre and Nguyen, Ryan and Xu, Andrew and Chen, Zijian and Zhang, Yilin and Chen, Yidi and Xian, Jasper and Lin, Jimmy},
year={2025},
booktitle={Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2025)},
location={Padova, Italy}
}

@inproceedings{sharifymoghaddam-etal-2025-unirag,
title = "{U}ni{RAG}: Universal Retrieval Augmentation for Large Vision Language Models",
author = "Sharifymoghaddam, Sahel and
Upadhyay, Shivani and
Chen, Wenhu and
Lin, Jimmy",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics (NAACL 2025)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.108/",
pages = "2026--2039",
ISBN = "979-8-89176-195-7",
abstract = "Recently, Large Vision Language Models (LVLMs) have unlocked many complex use cases that require Multi-Modal (MM) understanding (e.g., image captioning or visual question answering) and MM generation (e.g., text-guided image generation or editing) capabilities. To further improve the output fidelity of LVLMs we introduce UniRAG, a plug-and-play technique that adds relevant retrieved information to prompts as few-shot examples during inference. Unlike the common belief that Retrieval Augmentation (RA) mainly improves generation or understanding of uncommon entities, our evaluation results on the MSCOCO dataset with common entities show that both proprietary models like GPT-4o and Gemini-Pro and smaller open-source models like LLaVA, LaVIT, and Emu2 significantly enhance their generation quality when their input prompts are augmented with relevant information retrieved by Vision-Language (VL) retrievers like UniIR models. All the necessary code to reproduce our results is available at https://github.com/castorini/UniRAG."
}

@article{sharifymoghaddam2025chatbot,
title={Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses},
author={Sharifymoghaddam, Sahel and Upadhyay, Shivani and Thakur, Nandan and Pradeep, Ronak and Lin, Jimmy},
journal={arXiv preprint arXiv:2504.20006},
year={2025}
}

@inproceedings{pradeep2025ragnarok,
title={Ragnar{\"o}k: A reusable RAG framework and baselines for TREC 2024 retrieval-augmented generation track},
author={Pradeep, Ronak and Thakur, Nandan and Sharifymoghaddam, Sahel and Zhang, Eric and Nguyen, Ryan and Campos, Daniel and Craswell, Nick and Lin, Jimmy},
booktitle={European Conference on Information Retrieval (ECIR 2025)},
pages={132--148},
year={2025},
organization={Springer}
}

@article{pradeep2023rankzephyr,
title={RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!},
author={Pradeep, Ronak and Sharifymoghaddam, Sahel and Lin, Jimmy},
journal={arXiv preprint arXiv:2312.02724},
year={2023}
}

@article{pradeep2023rankvicuna,
title={Rankvicuna: Zero-shot listwise document reranking with open-source large language models},
author={Pradeep, Ronak and Sharifymoghaddam, Sahel and Lin, Jimmy},
journal={arXiv preprint arXiv:2309.15088},
year={2023}
}