# Explaining Relationships Among Research Papers

arXiv: https://arxiv.org/abs/2402.13426 · HTML: https://mlsanity.com/paper/2402.13426/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 67 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [What the DAAM: Interpreting Stable Diffusion Using Cross Attention](https://mlsanity.com/paper/2210.04885/) (2022)
- [Provable Meta-Learning of Linear Representations](https://mlsanity.com/paper/2002.11684/) (2020)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks](https://mlsanity.com/paper/1909.01716/) (2019)
- [Understanding Hard Negatives in Noise Contrastive Estimation](https://mlsanity.com/paper/2104.06245/) (2021)
- [Explaining Relationships Between Scientific Documents](https://mlsanity.com/paper/2002.00317/) (2020)
- [Investigating self-supervised learning for speech enhancement and separation](https://mlsanity.com/paper/2203.07960/) (2022)
- [Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents](https://mlsanity.com/paper/2106.00130/) (2021)
- [MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting](https://mlsanity.com/paper/2107.00414/) (2021)
- [Explanation-based Finetuning Makes Models More Robust to Spurious Cues](https://mlsanity.com/paper/2305.04990/) (2023)
- [Target-aware Abstractive Related Work Generation with Contrastive Learning](https://mlsanity.com/paper/2205.13339/) (2022)
- [CORWA: A Citation-Oriented Related Work Annotation Dataset](https://mlsanity.com/paper/2205.03512/) (2022)
- [Computing Medial Axis Transform with Feature Preservation via Restricted Power Diagram](https://mlsanity.com/paper/2210.13676/) (2022)
- [CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval](https://mlsanity.com/paper/2209.02071/) (2022)
- [Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation](https://mlsanity.com/paper/2104.05801/) (2021)
- [Reinforcement Learning with Automated Auxiliary Loss Search](https://mlsanity.com/paper/2210.06041/) (2022)
- [Learning ASR pathways: A sparse multilingual ASR model](https://mlsanity.com/paper/2209.05735/) (2022)
- [Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction](https://mlsanity.com/paper/2302.03793/) (2023)
- [Neural Related Work Summarization with a Joint Context-driven Attention Mechanism](https://mlsanity.com/paper/1901.09492/) (2019)
- [The CL-SciSumm Shared Task 2018: Results and Key Insights](https://mlsanity.com/paper/1909.00764/) (2019)
- [Few-Shot Document-Level Event Argument Extraction](https://mlsanity.com/paper/2209.02203/) (2022)
- [Parameter-Efficient Tuning with Special Token Adaptation](https://mlsanity.com/paper/2210.04382/) (2022)

## Built on by (most cited first, 3 of 3)

- [Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation](https://mlsanity.com/paper/2502.05151/) (2025)
- [Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models](https://mlsanity.com/paper/2508.15396/) (2025)
- [Modelling and Classifying the Components of a Literature Review](https://mlsanity.com/paper/2508.04337/) (2025)

## Abstract (arXiv)

Due to the rapid pace of research publications, keeping up to date with all the latest related papers is very time-consuming, even with daily feed tools. There is a need for automatically generated, short, customized literature reviews of sets of papers to help researchers decide what to read. While several works in the last decade have addressed the task of explaining a single research paper, usually in the context of another paper citing it, the relationship among multiple papers has been ignored; prior works have focused on generating a single citation sentence in isolation, without addressing the expository and transition sentences needed to connect multiple papers in a coherent story. In this work, we explore a feature-based, LLM-prompting approach to generate richer citation texts, as well as generating multiple citations at once to capture the complex relationships among research papers. We perform an expert evaluation to investigate the impact of our proposed features on the quality of the generated paragraphs and find a strong correlation between human preference and integrative writing style, suggesting that humans prefer high-level, abstract citations, with transition sentences between them to provide an overall story.