遊戲對話的去刻板化：在基於大型語言模型的NPC中平衡角色真實性與任務執行

摘要

大型語言模型（LLMs）的出現為遊戲環境中創建動態非玩家角色（NPCs）開闢了新機遇，使其既能執行功能性任務，又能生成符合角色設定的對話。本文中，我們（Tu_Character_lab）報告了參與2025年第二輪常識角色對話挑戰賽（CPDC）的情況，該賽事在三個賽道上評估智能體：任務導向對話、上下文感知對話及其整合。我們的方法結合了兩種互補策略：(i) 在API賽道中採用輕量級提示技術，包括一種去角色化提示方法，以抑制過度角色扮演並提升任務忠實度；(ii) 在GPU賽道中利用Qwen3-14B模型進行監督微調（SFT）和低秩適應（LoRA）的微調大模型。我們的最佳提交在任務1中排名第2，在API賽道的任務3中排名第2，在GPU賽道的任務3中排名第4。

English

The emergence of large language models (LLMs) has opened new opportunities for cre- ating dynamic non-player characters (NPCs) in gaming environments, enabling both func- tional 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 eval- uates 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).

遊戲對話的去刻板化：在基於大型語言模型的NPC中平衡角色真實性與任務執行

Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs

摘要

Support