paper-with-me

홈 › Papers

BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model

2024-08-20 · Yeyong Yu, Runsheng Yu, Haojie Wei, Zhanqiu Zhang, Quan Qian

The rapid advancement of large language models (LLMs) has revolutionized role-playing, enabling the development of general role-playing models. However, current role-playing training has two significant issues: (I) Using a predefined role profile to prompt dialogue training for specific scenarios usually leads to inconsistencies and even conflicts between the dialogue and the profile, resulting in training biases. (II) The model learns to imitate the role based solely on the profile, neglecting profile-dialogue alignment at the sentence level. In this work, we propose a simple yet effective framework called BEYOND DIALOGUE, designed to overcome these hurdles. This framework innovatively introduces "beyond dialogue" tasks to align dialogue with profile traits based on each specific scenario, thereby eliminating biases during training. Furthermore, by adopting an innovative prompting mechanism that generates reasoning outcomes for training, the framework allows the model to achieve fine-grained alignment between profile and dialogue at the sentence level. The aforementioned methods are fully automated and low-cost. Additionally, the integration of automated dialogue and objective evaluation methods forms a comprehensive framework, paving the way for general role-playing. Experimental results demonstrate that our model excels in adhering to and reflecting various dimensions of role profiles, outperforming most proprietary general and specialized role-playing baselines. All code and datasets are available at https://github.com/yuyouyu32/BeyondDialogue.

📄 PDF Abstract BibTeX arXiv:2408.10903

Code (1)

yuyouyu32/beyonddialogue 공식 구현

Tasks

Language ModelingLanguage ModellingSentence

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning

2024-03-05 · Chuanqi Cheng, Quan Tu, Shuo Shang, Cunli Mao 외

Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal…

Dialogue Generation

Persona-Aware Alignment Framework for Personalized Dialogue Generation

2025-11-13 · Guanrong Li, Xinyu Liu, Zhen Wu, Xinyu Dai arxiv

Personalized dialogue generation aims to leverage persona profiles and dialogue history to generate persona-relevant and consistent responses. Mainstream models typically rely on token-level language model training with …

Dialogue Generation

Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions

2026-06-05 · Xinyi Liu, Rinat Khaziev, Hooshang Nayyeri, Emine Yilmaz 외 arxiv

Synthetic dialogue corpora are increasingly used as proxies for target dialogue data, yet persona-grounded generators optimize individual conversations rather than corpus composition, yielding locally plausible dialogues…

Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager

2025-06-24 · Lucie Galland, Catherine Pelachaud, Florian Pecune

In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to…

Hierarchical Reinforcement LearningMeta-Learning

Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment

2025-05-21 · Weixiang Zhao, Xingyu Sui, Yulin Hu, Jiahe Guo 외

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they f…