Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.13586 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908613969182720 |
|---|---|
| author | Buakhaw, Pasin Kerdthaisong, Kun Phenhiran, Phuree Khlaisamniang, Pitikorn Vorathammathorn, Supasate Ittichaiwong, Piyalitt Yongsatianchot, Nutchanon |
| author_facet | Buakhaw, Pasin Kerdthaisong, Kun Phenhiran, Phuree Khlaisamniang, Pitikorn Vorathammathorn, Supasate Ittichaiwong, Piyalitt Yongsatianchot, Nutchanon |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13586 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs Buakhaw, Pasin Kerdthaisong, Kun Phenhiran, Phuree Khlaisamniang, Pitikorn Vorathammathorn, Supasate Ittichaiwong, Piyalitt Yongsatianchot, Nutchanon Computation and Language Artificial Intelligence 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). |
| title | Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.13586 |