{"ID":2855235,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13586","arxiv_id":"2510.13586","title":"Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs","abstract":"The emergence of large language models (LLMs) has opened new opportunities for creating dynamic non-player characters (NPCs) in gaming environments, enabling both functional task execution and persona-consistent dialogue generation. In this paper, we (Tu_Character_lab) report our participation in the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025 Round 2, which evaluates agents across three tracks: task-oriented dialogue, context-aware dialogue, and their integration. Our approach combines two complementary strategies: (i) lightweight prompting techniques in the API track, including a Deflanderization prompting method to suppress excessive role-play and improve task fidelity, and (ii) fine-tuned large models in the GPU track, leveraging Qwen3-14B with supervisedfinetuning (SFT) and Low-Rank Adaptation(LoRA). Our best submissions ranked 2nd on Task 1, 2nd on Task 3 (API track), and 4th on Task 3 (GPU track).","short_abstract":"The emergence of large language models (LLMs) has opened new opportunities for creating dynamic non-player characters (NPCs) in gaming environments, enabling both functional task execution and persona-consistent dialogue generation. In this paper, we (Tu_Character_lab) report our participation in the Commonsense Person...","url_abs":"https://arxiv.org/abs/2510.13586","url_pdf":"https://arxiv.org/pdf/2510.13586v3","authors":"[\"Pasin Buakhaw\",\"Kun Kerdthaisong\",\"Phuree Phenhiran\",\"Pitikorn Khlaisamniang\",\"Supasate Vorathammathorn\",\"Piyalitt Ittichaiwong\",\"Nutchanon Yongsatianchot\"]","published":"2025-10-15T14:17:23Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}