# Target-aware Abstractive Related Work Generation with Contrastive Learning

arXiv: https://arxiv.org/abs/2205.13339 · HTML: https://mlsanity.com/paper/2205.13339/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [An efficient framework for learning sentence representations](https://mlsanity.com/paper/1803.02893/) (2018)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Interventional Video Grounding with Dual Contrastive Learning](https://mlsanity.com/paper/2106.11013/) (2021)
- [Self-Supervised Contrastive Learning for Code Retrieval and Summarization via Semantic-Preserving Transformations](https://mlsanity.com/paper/2009.02731/) (2020)
- [CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation](https://mlsanity.com/paper/2109.05261/) (2021)
- [One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles](https://mlsanity.com/paper/2108.09355/) (2021)
- [SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression](https://mlsanity.com/paper/2007.08954/) (2020)
- [Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking](https://mlsanity.com/paper/2108.10510/) (2021)
- [From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information](https://mlsanity.com/paper/2005.04684/) (2020)
- [How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing](https://mlsanity.com/paper/1909.08837/) (2019)
- [Iterative Document Representation Learning Towards Summarization with Polishing](https://mlsanity.com/paper/1809.10324/) (2018)
- [Neural Related Work Summarization with a Joint Context-driven Attention Mechanism](https://mlsanity.com/paper/1901.09492/) (2019)
- [Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension](https://mlsanity.com/paper/2012.07410/) (2020)

## Built on by (most cited first, 20 of 20)

- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary](https://mlsanity.com/paper/2403.02574/) (2024)
- [Related Work and Citation Text Generation: A Survey](https://mlsanity.com/paper/2404.11588/) (2024)
- [P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task](https://mlsanity.com/paper/2409.11279/) (2024)
- [Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition](https://mlsanity.com/paper/2402.12255/) (2024)
- [Systematic Task Exploration with LLMs: A Study in Citation Text Generation](https://mlsanity.com/paper/2407.04046/) (2024)
- [EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator](https://mlsanity.com/paper/2301.00972/) (2023)
- [OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources](https://mlsanity.com/paper/2405.01930/) (2024)
- [Expert Preference-based Evaluation of Automated Related Work Generation](https://mlsanity.com/paper/2508.07955/) (2025)
- [Causal Intervention for Abstractive Related Work Generation](https://mlsanity.com/paper/2305.13685/) (2023)
- [Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generation](https://mlsanity.com/paper/2505.19647/) (2025)
- [AcademicEval: Live Long-Context LLM Benchmark](https://mlsanity.com/paper/2510.17725/) (2025)
- [Explaining Relationships Among Research Papers](https://mlsanity.com/paper/2402.13426/) (2024)
- [Unify Graph Learning with Text: Unleashing LLM Potentials for Session Search](https://mlsanity.com/paper/2505.14156/) (2025)
- [Comparing Apples to Apples: Generating Aspect-Aware Comparative Sentences from User Reviews](https://mlsanity.com/paper/2307.03691/) (2023)
- [Disentangling Instructive Information from Ranked Multiple Candidates for Multi-Document Scientific Summarization](https://mlsanity.com/paper/2404.10416/) (2024)
- [Modelling and Classifying the Components of a Literature Review](https://mlsanity.com/paper/2508.04337/) (2025)
- [From Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews](https://mlsanity.com/paper/2512.11661/) (2025)
- [Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation](https://mlsanity.com/paper/2609.15721/) (2026)

## Abstract (arXiv)

The related work section is an important component of a scientific paper, which highlights the contribution of the target paper in the context of the reference papers. Authors can save their time and effort by using the automatically generated related work section as a draft to complete the final related work. Most of the existing related work section generation methods rely on extracting off-the-shelf sentences to make a comparative discussion about the target work and the reference papers. However, such sentences need to be written in advance and are hard to obtain in practice. Hence, in this paper, we propose an abstractive target-aware related work generator (TAG), which can generate related work sections consisting of new sentences. Concretely, we first propose a target-aware graph encoder, which models the relationships between reference papers and the target paper with target-centered attention mechanisms. In the decoding process, we propose a hierarchical decoder that attends to the nodes of different levels in the graph with keyphrases as semantic indicators. Finally, to generate a more informative related work, we propose multi-level contrastive optimization objectives, which aim to maximize the mutual information between the generated related work with the references and minimize that with non-references. Extensive experiments on two public scholar datasets show that the proposed model brings substantial improvements over several strong baselines in terms of automatic and tailored human evaluations.