mlsanityData to 7 Oct 2026

Ontologically Faithful Generation of Non-Player Character Dialogues

arXiv 2212.10618 ↗First posted 20 Dec 2022cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

We introduce a language generation task grounded in a popular video game environment. KNUDGE (KNowledge Constrained User-NPC Dialogue GEneration) requires models to produce trees of dialogue between video game characters that accurately reflect quest and entity specifications stated in natural language. KNUDGE is constructed from side quest dialogues drawn directly from game data of Obsidian Entertainment's The Outer Worlds, leading to real-world complexities in generation: (1) dialogues are branching trees as opposed to linear chains of utterances; (2) utterances must remain faithful to the game lore -- character personas, backstories, and entity relationships; and (3) a dialogue must accurately reveal new quest details to the human player. We report results for a set of neural generation models using supervised and in-context learning techniques; we find competent performance but room for future work addressing the challenges of creating realistic, game-quality dialogues.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 28 of its 192 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

28 of 192 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  5. 2018QuAC : Question Answering in Contextcited by 379
  6. 2021Explaining Answers with Entailment Treescited by 148
  7. 2018Training Millions of Personalized Dialogue Agentscited by 126
  8. 2019Learning to Speak and Act in a Fantasy Text Adventure Gamecited by 122
  9. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  10. 2019Proactive Human-Machine Conversation with Explicit Conversation Goalscited by 87
  11. 2019ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisonscited by 83
  12. 2020STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generationcited by 56
16 more
  1. 2022Dialog Inpainting: Turning Documents into Dialogscited by 56
  2. 2022Dungeons and Dragons as a Dialog Challenge for Artificial Intelligencecited by 35
  3. 2021OTTers: One-turn Topic Transitions for Open-Domain Dialoguecited by 29
  4. 2020Dialogue Graph Modeling for Conversational Machine Readingcited by 26
  5. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17
  6. 2021Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systemscited by 14
  7. 2019Generating Interactive Worlds with Textcited by 13
  8. 2021Telling Stories through Multi-User Dialogue by Modeling Character Relationscited by 13
  9. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  10. 2022Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentationcited by 8
  11. 2020Facts2Story: Controlling Text Generation by Key Factscited by 7
  12. 2020Dialog Simulation with Realistic Variations for Training Goal-Oriented Conversational Systemscited by 4
  13. 2021TVStoryGen: A Dataset for Generating Stories with Character Descriptionscited by 4
  14. 2021Automated Story Generation as Question-Answeringcited by 3
  15. 2022Leveraging Natural Supervision for Language Representation Learning and Generationcited by 2
  16. 2017Automating Direct Speech Variations in Stories and Gamescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 2; 2026: 1.

7 papers.

  1. 2025RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrievalcited by 7
  2. 2023Tachikuma: Understading Complex Interactions with Multi-Character and Novel Objects by Large Language Modelscited by 5
  3. 2023Interpreting User Requests in the Context of Natural Language Standing Instructionscited by 5
  4. 2024AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agentscited by 2
  5. 2024Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domaincited by 2
  6. 2025Shall We Play a Game? Language Models for Open-ended Wargamescited by 1
  7. 2026Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generationcited by 0