# Cited Text Spans for Citation Text Generation

arXiv: https://arxiv.org/abs/2309.06365 · HTML: https://mlsanity.com/paper/2309.06365/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 51 references that are in the map.
- First posted on arXiv 12 Sep 2023.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks](https://mlsanity.com/paper/1909.01716/) (2019)
- [Explaining Relationships Between Scientific Documents](https://mlsanity.com/paper/2002.00317/) (2020)
- [Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity](https://mlsanity.com/paper/2111.08366/) (2021)
- [Syntactic Scaffolds for Semantic Structures](https://mlsanity.com/paper/1808.10485/) (2018)
- [CORWA: A Citation-Oriented Related Work Annotation Dataset](https://mlsanity.com/paper/2205.03512/) (2022)
- [How to best use Syntax in Semantic Role Labelling](https://mlsanity.com/paper/1906.00266/) (2019)
- [The CL-SciSumm Shared Task 2018: Results and Key Insights](https://mlsanity.com/paper/1909.00764/) (2019)
- [Automatic Related Work Generation: A Meta Study](https://mlsanity.com/paper/2201.01880/) (2022)

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

- [Modelling and Classifying the Components of a Literature Review](https://mlsanity.com/paper/2508.04337/) (2025)

## Abstract (arXiv)

An automatic citation generation system aims to concisely and accurately describe the relationship between two scientific articles. To do so, such a system must ground its outputs to the content of the cited paper to avoid non-factual hallucinations. Due to the length of scientific documents, existing abstractive approaches have conditioned only on cited paper abstracts. We demonstrate empirically that the abstract is not always the most appropriate input for citation generation and that models trained in this way learn to hallucinate. We propose to condition instead on the cited text span (CTS) as an alternative to the abstract. Because manual CTS annotation is extremely time- and labor-intensive, we experiment with distant labeling of candidate CTS sentences, achieving sufficiently strong performance to substitute for expensive human annotations in model training, and we propose a human-in-the-loop, keyword-based CTS retrieval approach that makes generating citation texts grounded in the full text of cited papers both promising and practical.