Contributed by Yingpeng Ma
This repository collects an extensive list of awesome papers about Story Generation / Storytelling, primarily focusing on the era of Large Language Models (LLMs).
All papers are sorted in chronological order, with the most recent ones appearing at the top.
We would like to extend our heartfelt gratitude to 「 Awesome-story-generation 」, 「 PaperForONLG 」 for their invaluable assistance and contributions.
Open issues and make PRs freely! If you have any suggestions or questions, please do not hesitate to reach out to me:
mayingpeng33 [AT] gmail [DOT] com
| Awesome-LLM-Characters |
|---|
Eg. ACL-2023 Title [paper] [code] .. [authors]
Neurocomputing-2023Open-world story generation with structured knowledge enhancement: A comprehensive survey [paper] [Yuxin Wang, Jieru Lin, Zhiwei Yu, Wei Hu, Börje F. Karlsson]NeurIPS-2022Factuality Enhanced Language Models for Open-Ended Text Generation [paper] [Nayeon Lee, Wei Ping, Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro]ArXiv-2022Survey: Automatic Movie Plot and Script Generation [paper] [Prerak Gandhi, Pushpak Bhattacharyya]ArXiv-2021Automatic Story Generation: Challenges and Attempts [paper] [Amal Alabdulkarim, Siyan Li, Xiangyu Peng]
ACL WNU-2022Uncovering Surprising Event Boundaries in Narratives [paper] [Zhilin Wang, Anna Jafarpour, Maarten Sap]AAAI-2020Story Realization: Expanding Plot Events into Sentences [paper] [code] [Prithviraj Ammanabrolu, Ethan Tien, Wesley Cheung, Zhaochen Luo, William Ma, Lara J. Martin, Mark O. Riedl]AAAI-2018Event Representations for Automated Story Generation with Deep Neural Nets [paper] [code] [Lara J. Martin, Prithviraj Ammanabrolu, Xinyu Wang, William Hancock, Shruti Singh, Brent Harrison, Mark O. Riedl]
ArXiv-2023Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers [paper] [Tuhin Chakrabarty, Vishakh Padmakumar, Faeze Brahman, Smaranda Muresan]ACL-2023Open-ended Long Text Generation via Masked Language Modeling [paper] [Xiaobo Liang, Zecheng Tang, Juntao Li, Min Zhang]ArXiv-2022Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers [paper] [Daphne Ippolito, Ann Yuan, Andy Coenen, Sehmon Burnam]EMNLP-2022Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing [paper] [Tuhin Chakrabarty, Vishakh Padmakumar, He He]EMNLP-2022EtriCA: Event-triggered context-aware story generation augmented by cross attention [paper] [Chen Tang, Chenghua Lin, Henglin Huang, Frank Guerin, Zhihao Zhang]AACL-2022Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics [paper] [Henglin Huang, Chen Tang, Tyler Loakman, Frank Guerin, Chenghua Lin]ArXiv-2022Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework [paper] [Jian Guan, Zhenyu Yang, Rongsheng Zhang, Zhipeng Hu, Minlie Huang]ArXiv-2022Great Expectations: Unsupervised Inference of Suspense, Surprise and Salience in Storytelling [paper] [David Wilmot]NAACL-2022Aligning to Social Norms and Values in Interactive Narratives [paper] [Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi]ICASSP-2022Clseg: Contrastive learning of story ending generation [paper] [Yuqiang Xie, Yue Hu, Luxi Xing, Yunpeng Li, Wei Peng, Ping Guo]ICML-2022Towards Coherent and Consistent Use of Entities in Narrative Generation [paper] [Pinelopi Papalampidi, Kris Cao, Tomas Kocisky]EMNLP-2021Guiding Neural Story Generation with Reader Models [paper] [Xiangyu Peng, Kaige Xie, Amal Alabdulkarim, Harshith Kayam, Samihan Dani, Mark O. Riedl]ArXiv-2021Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning [paper] [Amal Alabdulkarim, Winston Li, Lara J. Martin, Mark O. Riedl]EMNLP Findings-2021Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering [paper] [code] [Zhe Lin, Yitao Cai, Xiaojun Wan]ACL-2021Long text generation by modeling sentence-level and discourse-level coherence [paper] [Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang]CHI-2020Heteroglossia: In-Situ Story Ideation with the Crowd [paper] [Chieh-Yang Huang, Shih-Hong Huang, Ting-Hao 'Kenneth' Huang]EMNLP-2020Improving Neural Story Generation by Targeted Common Sense Grounding [paper] [Huanru Henry Mao, Bodhisattwa Prasad Majumder, Julian McAuley, Garrison W. Cottrell]ACL-2019Learning to Control the Fine-grained Sentiment for Story Ending Generation [paper] [Fuli Luo, Damai Dai, Pengcheng Yang, Tianyu Liu, Baobao Chang, Zhifang Sui, Xu Sun]AAAI-2019Story Ending Generation with Incremental Encoding and Commonsense Knowledge [paper] [Jian Guan, Yansen Wang, Minlie Huang]
ArXiv-2023Controlling keywords and their positions in text generation [paper]COLING-2022Psychology-guided Controllable Story Generation [paper] [Yuqiang Xie, Yue Hu, Yunpeng Li, Guanqun Bi, Luxi Xing, Wei Peng]WWW-2022Genre-controllable story generation via supervised contrastive learning [paper] [JinUk Cho, MinSu Jeong, JinYeong Bak, Yun-Gyung Cheong]EMNLP Findings-2021A Plug-and-Play Method for Controlled Text Generation [paper] [code]ArXiv-2021Plug-and-Blend: A Framework for Plug-and-play Controllable Story Generation with Sketches [paper] [code]ACL-2018Towards Controllable Story Generation [paper]
EMNLP-2022Towards Inter-character Relationship-driven Story Generation [paper]COLING-2022CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions [paper] [Xinpeng Wang, Han Jiang, Zhihua Wei, Shanlin Zhou]ArXiv-2022An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characters [paper] [Xinyu Jiang, Qi Zhang, Chongyang Shi, Kaiying Jiang, Liang Hu, Shoujin Wang]NAACL-2022TVShowGuess: Character Comprehension in Stories as Speaker Guessing [paper] [Yisi Sang, Xiangyang Mou, Mo Yu, Shunyu Yao, Jing Li, Jeffrey Stanton]NAACL-2022Persona-Guided Planning for Controlling the Protagonist’s Persona in Story Generation [paper] [code] [Zhexin Zhang, Jiaxin Wen, Jian Guan, Minlie Huang]ArXiv-2021Modeling Worlds in Text [paper]ACL-2021Unsupervised Enrichment of Persona-grounded Dialog with Background Stories [paper] [Bodhisattwa Prasad Majumder, Taylor Berg-Kirkpatrick, Julian McAuley, Harsh Jhamtani]ACL-2021Telling Stories through Multi-User Dialogue by Modeling Character Relations [paper]
ACL-2023StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing [paper] [Xuekai Zhu, Jian Guan, Minlie Huang, Juan Liu]ACL-2021Stylized story generation with style-guided planning [paper] [Xiangzhe Kong, Jialiang Huang, Ziquan Tung, Jian Guan, Minlie Huang]
ACL-2023DOC: Improving Long Story Coherence With Detailed Outline Control [paper] [Kevin Yang, Dan Klein, Nanyun Peng, Yuandong Tian]CHI-2022TaleBrush: Sketching Stories with Generative Pretrained Language Models [paper] [John Joon Young Chung, Wooseok Kim, Kang Min Yoo, Hwaran Lee, Eytan Adar, Minsuk Chang]ArXiv-2022Neural Story Planning [paper] [Anbang Ye, Christopher Cui, Taiwei Shi, Mark O. Riedl]ArXiv-2022Event Transition Planning for Open-ended Text Generation [paper] [Qintong Li, Piji Li, Wei Bi, Zhaochun Ren, Yuxuan Lai, Lingpeng Kong]AAAI-2020Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder [paper] [Meng-Hsuan Yu, Juntao Li, Danyang Liu, Dongyan Zhao, Rui Yan, Bo Tang, Haisong Zhang]ArXiv-2019Strategies for Structuring Story Generation [paper]AAAI-2019Plan-And-Write: Towards Better Automatic Storytelling [paper] [code]EMNLP-2018A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation [paper]ACL-2018Hierarchical Neural Story Generation [paper] [code] [Writing prompt]
ACL Findings-2023CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding [paper] [Yijiang River Dong, Lara J. Martin, Chris Callison-Burch]EMNLP-2022Re3: Generating longer stories with recursive reprompting and revision [paper] [Kevin Yang, Yuandong Tian, Nanyun Peng, Dan Klein]NAACL-2022Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts [paper] [Rujun Han, Hong Chen, Yufei Tian, Nanyun Peng]SIGIR-2022What makes the story forward? inferring commonsense explanations as prompts for future event generation [paper] [Li Lin, Yixin Cao, Lifu Huang, Shu'ang Li, Xuming Hu, Lijie Wen, Jianmin Wang]
ArXiv-2023RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text [paper] [code] [Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell, Mrinmaya Sachan ]INLG-2023The Next Chapter: A Study of Large Language Models in Storytelling [paper] [Zhuohan Xie, Trevor Cohn, Jey Han Lau]ArXiv-2023Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models [paper] [Evgeniia Razumovskaia, Joshua Maynez, Annie Louis, Mirella Lapata, Shashi Narayan]CHI-2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals [paper] [Piotr Mirowski, Kory W. Mathewson, Jaylen Pittman, Richard Evans]ArXiv-2022Plot Writing From Pre-Trained Language Models [paper] [Yiping Jin, Vishakha Kadam, Dittaya Wanvarie]EMNLP-2020MEGATRON-CNTRL: Controllable story generation with external knowledge using large-scale language models [paper] [Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Raul Puri, Pascale Fung, Anima Anandkumar, Bryan Catanzaro]TACL-2020A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation [paper] [Jian Guan, Fei Huang, Zhihao Zhao, Xiaoyan Zhu, Minlie Huang]
ArXiv-2023Learning Personalized Story Evaluation [paper] [Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian]ArXiv-2023Art or Artifice? Large Language Models and the False Promise of Creativity [paper] [Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal, Smaranda Muresan, Chien-Sheng Wu]ACL-2023HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation [paper] [Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, Yunwen Chen]ACL-2023Can Large Language Models Be an Alternative to Human Evaluations? [paper] [Cheng-Han Chiang, Hung-yi Lee]ArXiv-2023Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study [paper] [Yi Chen, Rui Wang, Haiyun Jiang, Shuming Shi, Ruifeng Xu]ArXiv-2023DeltaScore: Evaluating Story Generation with Differentiating Perturbations [paper] [Zhuohan Xie, Miao Li, Trevor Cohn, Jey Han Lau]EMNLP-2022Automatic Comment Generation for Chinese Student Narrative Essays [paper] [Zhexin Zhang, Jian Guan, Guowei Xu, Yixiang Tian, Minlie Huang]EMNLP-2022StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning [paper] [Hong Chen, Duc Minh Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama]ArXiv-2022A Benchmark for Understanding and Generating Dialogue between Characters in Stories [paper] [Jianzhu Yao, Ziqi Liu, Jian Guan, Minlie Huang]ArXiv-2022The Glass Ceiling of Automatic Evaluation in Natural Language Generation [paper] [Pierre Colombo, Maxime Peyrard, Nathan Noiry, Robert West, Pablo Piantanida]COLING-2022Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation [paper] [Cyril Chhun, Pierre Colombo, Chloé Clavel, Fabian M. Suchanek]ArXiv-2021Toward Educator-focused Automated Scoring Systems for Reading and Writing [paper] [Mike Hardy]TACL-2022LOT: A story-centric benchmark for evaluating Chinese long text understanding and generation [paper] [Jian Guan, Zhuoer Feng, Yamei Chen, Ruilin He, Xiaoxi Mao, Changjie Fan, Minlie Huang]ACL-2021Openmeva: A benchmark for evaluating open-ended story generation metrics [paper] [Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang]EMNLP-2020Union: An unreferenced metric for evaluating open-ended story generation [paper] [Jian Guan, Minlie Huang]
FDG-2022TropeTwist: Trope-based Narrative Structure Generation [paper] [Alberto Alvarez, Jose Font]AAAI-2020Generating Interactive Worlds with Text [paper] [Angela Fan, Jack Urbanek, Pratik Ringshia, Emily Dinan, Emma Qian, Siddharth Karamcheti, Shrimai Prabhumoye, Douwe Kiela, Tim Rocktaschel, Arthur Szlam, Jason Weston]EMNLP-2019Learning to Speak and Act in a Fantasy Text Adventure Game [paper] [Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, Jason Weston]IJCAI-2018TextWorld: A Learning Environment for Text-based Game [paper] [Marc-Alexandre Côté, Ákos Kádár, Xingdi Yuan, Ben Kybartas, Tavian Barnes, Emery Fine, James Moore, Matthew Hausknecht, Layla El Asri, Mahmoud Adada, Wendy Tay, Adam Trischler]
ACL-2023StoryWars: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation [paper] [Yulun Du, Lydia Chilton]INLG-2023Long Story Generation Challenge [paper] [Nikolay Mikhaylovskiy]ArXiv-2022PASTA: A Dataset for Modeling Participant States in Narratives [paper] [Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen, Francis Ferraro, Nathanael Chambers, Niranjan Balasubramanian]NAACL-2022A corpus for understanding and generating moral stories [paper] [Jian Guan, Ziqi Liu, Minlie Huang]ACL-2022SummScreen: A Dataset for Abstractive Screenplay Summarization [paper] [code] [Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel]NAACL-2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories [paper] [Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, James Allen]
- ROC Stories is a compilation of 100,000 five-sentence stories and 3,742 Story Cloze Test stories, capturing a rich array of causal and temporal commonsense connections between everyday events, making it suitable for story generation tasks.
- CommonGen was developed by combining crowdsourced and existing caption corpora, containing 79k commonsense descriptions across 35k distinct concept-sets.
- CMU Movie Summary Corpus offers access to a dataset containing movie plot summaries and related metadata.
- Scifi TV Show Plot Summaries & Events is a collection of plot synopses for long-running (80+ episodes) science fiction TV shows, sourced from Fandom.com wikis.
- The LIGHT project serves as a large-scale fantasy text adventure game research platform, designed to train agents capable of both talking and acting, while interacting with other models or humans.
- The TextWorld project is a sandbox learning environment aimed at training and evaluating reinforcement learning (RL) agents on text-based games.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent