paper-with-me

홈 › Papers

CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation

2024-01-02 · Quan Tu, Shilong Fan, Zihang Tian, Rui Yan

Recently, the advent of large language models (LLMs) has revolutionized generative agents. Among them, Role-Playing Conversational Agents (RPCAs) attract considerable attention due to their ability to emotionally engage users. However, the absence of a comprehensive benchmark impedes progress in this field. To bridge this gap, we introduce CharacterEval, a Chinese benchmark for comprehensive RPCA assessment, complemented by a tailored high-quality dataset. The dataset comprises 1,785 multi-turn role-playing dialogues, encompassing 23,020 examples and featuring 77 characters derived from Chinese novels and scripts. It was carefully constructed, beginning with initial dialogue extraction via GPT-4, followed by rigorous human-led quality control, and enhanced with in-depth character profiles sourced from Baidu Baike. CharacterEval employs a multifaceted evaluation approach, encompassing thirteen targeted metrics on four dimensions. Comprehensive experiments on CharacterEval demonstrate that Chinese LLMs exhibit more promising capabilities than GPT-4 in Chinese role-playing conversation. Source code, data source and reward model will be publicly accessible at https://github.com/morecry/CharacterEval.

📄 PDF Abstract BibTeX arXiv:2401.01275

Code (1)

morecry/charactereval 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents

2025-05-29 · Feiteng Fang, Ting-En Lin, Yuchuan Wu, Xiong Liu 외

Role-Playing Language Agents (RPLAs) aim to simulate characters for realistic and engaging human-computer interactions. However, traditional reward models often struggle with scalability and adapting to subjective conver…

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

2024-09-23 · Yihong Tang, Jiao Ou, Che Liu, Fuzheng Zhang 외

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…

Language ModelingLanguage ModellingLarge Language Model

SocialBench: Sociality Evaluation of Role-Playing Conversational Agents

2024-03-20 · Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu 외

Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has pre…

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization

2025-08-12 · Xinge Ye, Rui Wang, Yuchuan Wu, Victor Ma 외 arxiv

Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like rol…

Reinforcement LearningMathematical ReasoningCode Generation

Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

2026-06-25 · Zhenhua Xu, Dongsheng Chen, Jian Li, Yitong Lin 외 arxiv

Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant paradigm -- supervised fine-tuning -- encourages behavioral mimicry wit…

Reinforcement Learning