Ontologically Faithful Generation of Non-Player Character Dialogues
This addresses the challenge of creating realistic, lore-accurate dialogues for video game developers, but it is incremental as it builds on existing generation tasks with domain-specific constraints.
The paper tackled the problem of generating non-player character dialogues in video games that are faithful to game lore and quest specifications, introducing the KNUDGE task based on The Outer Worlds data, and found competent but improvable performance from neural models.
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.