# Citations as Queries: Source Attribution Using Language Models as Rerankers

arXiv: https://arxiv.org/abs/2306.17322 · HTML: https://mlsanity.com/paper/2306.17322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 7 of 7)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [Neural Ranking Models with Weak Supervision](https://mlsanity.com/paper/1704.08803/) (2017)
- [RELIC: Retrieving Evidence for Literary Claims](https://mlsanity.com/paper/2203.10053/) (2022)
- [Wikipedia Citations: A comprehensive dataset of citations with identifiers extracted from English Wikipedia](https://mlsanity.com/paper/2007.07022/) (2020)

## Built on by (most cited first, 1 of 1)

- [Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust](https://mlsanity.com/paper/2508.07095/) (2025)

## Abstract (arXiv)

This paper explores new methods for locating the sources used to write a text, by fine-tuning a variety of language models 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.