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

• URL: http://arxiv.org/abs/2510.13586v3
• Date: Sun, 26 Oct 2025 14:03:51 GMT
• Title: Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs
• Authors: Pasin Buakhaw, Kun Kerdthaisong, Phuree Phenhiran, Pitikorn Khlaisamniang, Supasate Vorathammathorn, Piyalitt Ittichaiwong, Nutchanon Yongsatianchot,
• Abstract summary: In this paper, we report our participation in the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025 Round 2.<n>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)
• Score: 2.2816872489992135
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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).

Related papers

• Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue [0.0]
  We present a system for creating Non-Player Characters (NPCs) capable of both natural dialogue and contextual action execution.<n>Our system comfortably meets the computational efficiency requirements, delivering fast responses and maintaining modest resource usage.
  arXiv  Detail & Related papers  (2025-11-03T16:28:47Z)
• Collaborative Problem-Solving in an Optimization Game [52.005042190810116]
  We introduce a novel dialogue game in which the agents collaboratively solve a two-player Traveling Salesman problem.<n>Our best agent solves 45% of games optimally in self-play.<n>It also demonstrates an ability to collaborate successfully with human users and generalize to unfamiliar graphs.
  arXiv  Detail & Related papers  (2025-05-21T13:15:35Z)
• Hybrid Voting-Based Task Assignment in Role-Playing Games [0.0]
  Voting-Based Task Assignment (VBTA) is a framework inspired by human reasoning in task allocation and completion.<n> VBTA efficiently identifies and assigns the most suitable agent to each task.<n>Our method shows promise when generating both unique combat encounters and narratives.
  arXiv  Detail & Related papers  (2025-02-25T22:58:21Z)
• Game Development as Human-LLM Interaction [55.03293214439741]
  This paper introduces the Chat Game Engine (ChatGE) powered by Human-LLM interaction.<n>ChatGE allows everyone to develop a custom game using natural language through Human-LLM interaction.<n>We construct a ChatGE for poker games as a case study and evaluate it from two perspectives: interaction quality and code correctness.
  arXiv  Detail & Related papers  (2024-08-18T07:06:57Z)
• A Dialogue Game for Eliciting Balanced Collaboration [64.61707514432533]
  We present a two-player 2D object placement game in which the players must negotiate the goal state themselves. We show empirically that human players exhibit a variety of role distributions, and that balanced collaboration improves task performance.
  arXiv  Detail & Related papers  (2024-06-12T13:35:10Z)
• Are LLMs Robust for Spoken Dialogues? [10.855403629160921]
  Large Pre-Trained Language Models have demonstrated state-of-the-art performance in different downstream tasks. Most of the publicly available datasets and benchmarks on task-oriented dialogues focus on written conversations. We have evaluated the performance of LLMs for spoken task-oriented dialogues on the DSTC11 test sets.
  arXiv  Detail & Related papers  (2024-01-04T14:36:38Z)
• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs [59.74002011562726]
  We propose a novel linguistic cue-based chain-of-thoughts (textitCue-CoT) to provide a more personalized and engaging response. We build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English. Empirical results demonstrate our proposed textitCue-CoT method outperforms standard prompting methods in terms of both textithelpfulness and textitacceptability on all datasets.
  arXiv  Detail & Related papers  (2023-05-19T16:27:43Z)
• Deploying a Retrieval based Response Model for Task Oriented Dialogues [8.671263996400844]
  Task-oriented dialogue systems need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates.
  arXiv  Detail & Related papers  (2022-10-25T23:10:19Z)
• Adding Chit-Chat to Enhance Task-Oriented Dialogues [36.93917437554091]
  Chit-Chat can be added to task-oriented dialogues to make virtual assistant conversations more engaging and interactive. We present our new chit-chat-based annotations to 23.8K dialogues from two popular task-oriented dialogue datasets. We also propose three new models for adding chit-chat to task-oriented dialogues, explicitly trained to predict user goals and to generate contextually relevant chit-chat responses.
  arXiv  Detail & Related papers  (2020-10-24T03:22:43Z)
• Video-Grounded Dialogues with Pretrained Generation Language Models [88.15419265622748]
  We leverage the power of pre-trained language models for improving video-grounded dialogue. We propose a framework by formulating sequence-to-grounded dialogue tasks as a sequence-to-grounded task. Our framework allows fine-tuning language models to capture dependencies across multiple modalities.
  arXiv  Detail & Related papers  (2020-06-27T08:24:26Z)
• TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue [113.45485470103762]
  In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling. To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
  arXiv  Detail & Related papers  (2020-04-15T04:09:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.