English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The advent of Large Language Models (LLMs) has paved the way for complextasks such as role-playing, which enhances user interactions by enabling modelsto imitate various characters. However, the closed-source nature ofstate-of-the-art LLMs and their general-purpose training limit role-playingoptimization. In this paper, we introduce RoleLLM, a framework to benchmark,elicit, and enhance role-playing abilities in LLMs. RoleLLM comprises fourstages: (1) Role Profile Construction for 100 roles; (2) Context-BasedInstruction Generation (Context-Instruct) for role-specific knowledgeextraction; (3) Role Prompting using GPT (RoleGPT) for speaking styleimitation; and (4) Role-Conditioned Instruction Tuning (RoCIT) for fine-tuningopen-source models along with role customization. By Context-Instruct andRoleGPT, we create RoleBench, the first systematic and fine-grainedcharacter-level benchmark dataset for role-playing with 168,093 samples.Moreover, RoCIT on RoleBench yields RoleLLaMA (English) and RoleGLM (Chinese),significantly enhancing role-playing abilities and even achieving comparableresults with RoleGPT (using GPT-4).

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models