ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning

• URL: http://arxiv.org/abs/2409.14710v2
• Date: Tue, 22 Oct 2024 09:00:19 GMT
• Title: ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning
• Authors: Yihong Tang, Jiao Ou, Che Liu, Fuzheng Zhang, Di Zhang, Kun Gai,
• Abstract summary: Role-playing is an emerging application in the field of Human-Computer Interaction (HCI) Despite significant progress, role-playing agents (RPLAs) still struggle with maintaining role-consistency across conversations. We present ERABAL, a framework aimed at enhancing RPLAs' role-playing capabilities through boundary-aware learning.
• Score: 17.5855800570993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Role-playing is an emerging application in the field of Human-Computer Interaction (HCI), primarily implemented through the alignment training of a large language model (LLM) with assigned characters. Despite significant progress, role-playing agents (RPLAs) still struggle with maintaining role-consistency across conversations, particularly when confronted with boundary queries subtly related to character attributes. In this paper, we present ERABAL, a framework aimed at enhancing RPLAs' role-playing capabilities through boundary-aware learning. ERABAL encompasses a generation pipeline for role-specific dialogues and a concomitant methodology for alignment training. Through comprehensive evaluations, we demonstrate that ERABAL is both efficient and effective. By training with significantly fewer dialogues than those used in leading approaches, ERABAL achieves notable improvements across WikiRoleEval, CharacterEval, and the role-playing subset of MT-Bench compared to the generalist baseline models. Our code and datasets will be made publicly available to support further research.

Related papers

• BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model [12.617285298415013]
  The rapid advancement of large language models (LLMs) has revolutionized role-playing, enabling the development of general role-playing models. Current role-playing training has two significant issues: (I) Using a predefined role profile to prompt dialogue training for specific scenarios leads to inconsistencies and even conflicts between the dialogue and the profile, resulting in training biases. We propose a simple yet effective framework called DIALOGUE, designed to overcome these hurdles.
  arXiv  Detail & Related papers  (2024-08-20T14:47:38Z)
• MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space [16.508815826492814]
  Traditional Personalized Dialogue Generation (PDG) relies on external role data, which can be scarce and raise privacy concerns. We introduce a novel framework textbfMOdels textbfRoles from textbfPersonalized Dialogue textbfHistory by textbfExploring and textbfUtilizing Latent textbfSpace (MORPHEUS) through a three-stage training process.
  arXiv  Detail & Related papers  (2024-07-02T15:12:34Z)
• Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data [58.92110996840019]
  We propose to enhance role-playing language models (RPLMs) via personality-indicative data. Specifically, we leverage questions from psychological scales and distill advanced RPAs to generate dialogues that grasp the minds of characters. Experimental results validate that RPLMs trained with our dataset exhibit advanced role-playing capabilities for both general and personality-related evaluations.
  arXiv  Detail & Related papers  (2024-06-27T06:24:00Z)
• Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions [62.0123588983514]
  Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields. We reformulate the peer-review process as a multi-turn, long-context dialogue, incorporating distinct roles for authors, reviewers, and decision makers. We construct a comprehensive dataset containing over 26,841 papers with 92,017 reviews collected from multiple sources.
  arXiv  Detail & Related papers  (2024-06-09T08:24:17Z)
• Prompt Framework for Role-playing: Generation and Evaluation [3.2845546753303867]
  Large language models (LLM) have demonstrated remarkable abilities in generating natural language, understanding user instruction, and mimicking human language use. We introduce a framework that uses prompts to leverage the state-of-the-art (SOTA) LLMs to construct role-playing dialogue datasets and evaluate the role-playing performance.
  arXiv  Detail & Related papers  (2024-06-02T06:09:56Z)
• Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement [17.5855800570993]
  Large Language Models (LLMs) have propelled dialogue generation into new realms, particularly in the field of role-playing systems (RPSs) Existing LLM-based RPSs still struggle to align with roles when handling intricate and trapped queries in boundary scenarios. We design the Modular ORchestrated Trap-setting Interaction SystEm (MORTISE) to benchmark and improve the role-playing LLMs' performance.
  arXiv  Detail & Related papers  (2024-02-16T12:12:05Z)
• Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment [62.898963074989766]
  We introduce Ditto, a self-alignment method for role-play. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold. We present the first comprehensive cross-supervision alignment experiment in the role-play domain.
  arXiv  Detail & Related papers  (2024-01-23T03:56:22Z)
• RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models [107.00832724504752]
  We introduce RoleLLM, a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models (LLMs) By Context-Instruct and RoleGPT, we create RoleBench, the first systematic and fine-grained character-level benchmark dataset for role-playing with 168,093 samples.
  arXiv  Detail & Related papers  (2023-10-01T17:52:59Z)
• JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning [53.83063435640911]
  Dialogue policy learning (DPL) is a crucial component of dialogue modelling. We introduce a novel framework, JoTR, to generate flexible dialogue actions. Unlike traditional methods, JoTR formulates a word-level policy that allows for a more dynamic and adaptable dialogue action generation.
  arXiv  Detail & Related papers  (2023-09-01T03:19:53Z)
• RODE: Learning Roles to Decompose Multi-Agent Tasks [69.56458960841165]
  Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. We propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. By virtue of these advances, our method outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark.
  arXiv  Detail & Related papers  (2020-10-04T09:20:59Z)

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.