Citations as Queries: Source Attribution Using Language Models as Rerankers
Abstract: This paper explores new methods for locating the sources used to write a text, by fine-tuning a variety of LLMs to rerank candidate sources. After retrieving candidates sources using a baseline BM25 retrieval model, a variety of reranking methods are tested to see how effective they are at the task of source attribution. We conduct experiments on two datasets, English Wikipedia and medieval Arabic historical writing, and employ a variety of retrieval and generation based reranking models. In particular, we seek to understand how the degree of supervision required affects the performance of various reranking models. We find that semisupervised methods can be nearly as effective as fully supervised methods while avoiding potentially costly span-level annotation of the target and source documents.
- Neural Ranking Models with Weak Supervision. CoRR abs/1704.08803 (2017). arXiv:1704.08803 http://arxiv.org/abs/1704.08803
- An Empirical Study of Pre-trained Transformers for Arabic Information Extraction. arXiv:2004.14519 [cs] (Nov. 2020). http://arxiv.org/abs/2004.14519 arXiv: 2004.14519.
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs/1910.13461 (2019). arXiv:1910.13461 http://arxiv.org/abs/1910.13461
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. CoRR abs/2005.11401 (2020). arXiv:2005.11401 https://arxiv.org/abs/2005.11401
- Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations. In Proceedings of the 44th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021). 2356–2362.
- Generation-Augmented Retrieval for Open-domain Question Answering. arXiv:2009.08553Â [cs.CL]
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. CoRR abs/1910.10683 (2019). arXiv:1910.10683 http://arxiv.org/abs/1910.10683
- Maxim Romanov and Masoumeh Seydi. 2019. OpenITI: a Machine-Readable Corpus of Islamicate Texts. https://doi.org/10.5281/zenodo.3082464
- Wikipedia Citations: A comprehensive dataset of citations with identifiers extracted from English Wikipedia. CoRR abs/2007.07022 (2020). arXiv:2007.07022 https://arxiv.org/abs/2007.07022
- Detecting and modeling local text reuse. In IEEE/ACM Joint Conference on Digital Libraries. 183–192. https://doi.org/10.1109/JCDL.2014.6970166
- RELIC: Retrieving Evidence for Literary Claims. arXiv:2203.10053Â [cs.CL]
- Jinzhu Zhang and Lipeng Zhu. 2022. Citation recommendation using semantic representation of cited papers’ relations and content. Expert Systems with Applications 187 (2022), 115826. https://doi.org/10.1016/j.eswa.2021.115826
Paper Prompts
Sign up for free to create and run prompts on this paper.