mlsanityData to 7 Oct 2026

CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding

arXiv 2212.10754 ↗First posted 21 Dec 2022cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Story generation and understanding -- as with all NLG/NLU tasks -- has seen a surge in neurosymbolic work. Researchers have recognized that, while large language models (LLMs) have tremendous utility, they can be augmented with symbolic means to be even better and to make up for any flaws that the neural networks might have. However, symbolic methods are extremely costly in terms of the amount of time and expertise needed to create them. In this work, we capitalize on state-of-the-art Code-LLMs, such as Codex, to bootstrap the use of symbolic methods for tracking the state of stories and aiding in story understanding. We show that our CoRRPUS system and abstracted prompting procedures can beat current state-of-the-art structured LLM techniques on pre-existing story understanding tasks (bAbI Task 2 and Re^3) with minimal hand engineering. We hope that this work can help highlight the importance of symbolic representations and specialized prompting for LLMs as these models require some guidance for performing reasoning tasks properly.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 52 of its 83 references that are in the map. First posted on arXiv 21 Dec 2022.

Builds on

52 of 83 references.

References · 52

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  11. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  12. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
38 more
  1. 2018Hierarchical Neural Story Generationcited by 1,182
  2. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  3. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  4. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  6. 2015Towards AI-Complete Question Answering: A Set of Prerequisite Toy Taskscited by 309
  7. 2019Automatic Detection of Generated Text is Easiest when Humans are Fooledcited by 260
  8. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  9. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  10. 2022Autoformalization with Large Language Modelscited by 252
  11. 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 232
  12. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  13. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  14. 2022Language Models of Code are Few-Shot Commonsense Learnerscited by 160
  15. 2020A Knowledge-Enhanced Pretraining Model for Commonsense Story Generationcited by 116
  16. 2020PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Trackingcited by 104
  17. 2019Do Massively Pretrained Language Models Make Better Storytellers?cited by 90
  18. 2019Counterfactual Story Reasoning and Generationcited by 87
  19. 2020GLUCOSE: GeneraLized and COntextualized Story Explanationscited by 85
  20. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
  21. 2020PyMT5: multi-mode translation of natural language and Python code with transformerscited by 80
  22. 2017Event Representations for Automated Story Generation with Deep Neural Netscited by 62
  23. 2018Controllable Neural Story Plot Generation via Reward Shapingcited by 49
  24. 2021"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understandingcited by 48
  25. 2019Plan, Write, and Revise: an Interactive System for Open-Domain Story Generationcited by 43
  26. 2019Story Realization: Expanding Plot Events into Sentencescited by 35
  27. 2022Dungeons and Dragons as a Dialog Challenge for Artificial Intelligencecited by 35
  28. 2021ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoningcited by 30
  29. 2021Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoningcited by 29
  30. 2021LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generationcited by 24
  31. 2022StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoningcited by 21
  32. 2020Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summariescited by 19
  33. 2021Is Everything in Order? A Simple Way to Order Sentencescited by 15
  34. 2021Salience-Aware Event Chain Modeling for Narrative Understandingcited by 14
  35. 2021Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learningcited by 14
  36. 2021Telling Stories through Multi-User Dialogue by Modeling Character Relationscited by 13
  37. 2021Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Storiescited by 11
  38. 2022Towards Inter-character Relationship-driven Story Generationcited by 11

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 1; 2026: 1.

7 papers.

  1. 2025Social World Modelscited by 14
  2. 2024GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasetscited by 12
  3. 2023Event Causality Is Key to Computational Story Understandingcited by 11
  4. 2024Large Language Models are Interpretable Learnerscited by 7
  5. 2024Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understandingcited by 2
  6. 2026CascadeMind at SemEval-2026 Task 4: A Hybrid Neuro-Symbolic Cascade for Narrative Similaritycited by 1
  7. 2024WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Modelscited by 0