Search Results for « Role-Play »

We present the use of two methods we believe warrant more use than they currently have in the field of human-robot interaction: role-play and Hierarchical Task Analysis. Some of its potential is showcased through our use of them in an ongoing research project which entails developing a robot application meant to assist at a community pharmacy. The two methods have provided us with several advantages. The role-playing provided a controlled and adjustable environment for understanding the customers' needs where pharmacists could act as models for the robot's behavior; and the Hierarchical Task Analysis ensured the behavior displayed was modelled correctly and aided development through facilitating co-design. Future research could focus on developing task analysis methods especially suited for social robot interaction.

Large Language Models (LLMs) have shown promise in character imitation, enabling immersive and engaging conversations. However, they often generate content that is irrelevant or inconsistent with a character's background. We attribute these failures to: (1) the inability to accurately recall character-specific knowledge due to entity ambiguity, and (2) a lack of awareness of the character's cognitive boundaries. To address these issues, we propose RoleRAG, a retrieval-based framework that integrates efficient entity disambiguation for knowledge indexing with a boundary-aware retriever for extracting contextually appropriate information from a structured knowledge graph. Experiments on role-playing benchmarks show that RoleRAG's calibrated retrieval helps both general-purpose and role-specific LLMs better align with character knowledge and reduce hallucinated responses.

This article compares educational role-play and role-playing games in education by examining their definition, similarities in their elements, differences current use, implication of the elements of educational role-play and role-playing games, along with phenomenon unique to role-playing activities shared by both. This article will also outline how elements of educational role-play and role-playing games can aid in implementation of transformative learning, along with precautions and special attention that must be taken to conduct a role-playing activity in education.

Since the COVID-19 pandemic, educational institutions have embarked on digital transformation projects. The success of these projects depends on integrating new technologies and understanding the needs of digitally literate students. The "learning by doing" approach suggests that real success in learning new skills is achieved when students can try out and practise these skills. In this article, we demonstrate how Large Language Models (LLMs) can enhance the quality of teaching by using ChatGPT in a role-playing simulation game scenario to promote active learning. Moreover, we discuss how LLMs can boost students' interest in learning by allowing them to practice real-life scenarios using ChatGPT.

This paper looks at the process of role-playing that takes place in various games. Role-play is a social activity, where three elements are always present: An imaginary game world, a power structure and personified player characters. In a nutshell, all role-playing activities about imaginary people acting out in an imaginary environment; the power structure is needed to differentiate these activities from free make-believe and children’s play. After the basics, the paper moves on to discuss the various components in detail, going through how rules, goals, worlds, power, information and identity function in role-play. While the paper does not lead to a simple conclusion, it seeks to present a solid foundation for further research.

The Conversation Analytic Role-play Method (CARM) is an approach to training based on conversation analytic evidence about the problems and roadblocks that can occur in institutional interaction. Traditional training often relies on role-played interaction, which differs systematically from the actual events it is meant to mimic and prepare for. In contrast, CARM uses animated audio and video recordings of real-time, actual encounters. CARM provides a unique framework for discussing and evaluating, in slow motion, actual talk as people do their jobs. It also provides an evidence base for making decisions about effective practice and communication policy in organizations. This article describes CARM’s distinctive practices and its impact on professional development across different organizations. Data are in British English.

Modern large language models (LLMs) exhibit a remarkable capacity for role-playing, enabling them to embody not only human characters but also non-human entities. This versatility allows them to simulate complex human-like interactions and behaviors within various contexts, as well as to emulate specific objects or systems. While these capabilities have enhanced user engagement and introduced novel modes of interaction, the influence of role-playing on LLMs' reasoning abilities remains underexplored. In this study, we introduce a strategically designed role-play prompting methodology and assess its performance under the zero-shot setting across twelve diverse reasoning benchmarks. Our empirical results illustrate that role-play prompting consistently surpasses the standard zero-shot approach across most datasets. Notably, in experiments conducted using ChatGPT, accuracy on AQuA rises from 53.5% to 63.8%, and on Last Letter from 23.8% to 84.2%.Upon further comparison with the Zero-Shot-CoT technique, which prompts the model to "think step by step", our study demonstrates that role-play prompting acts as a more effective trigger for the CoT process. This highlights its potential to augment the reasoning capabilities of LLMs. We release our code at https://github.com/NKU-HLT/Role-Play-Prompting.

Role-playing games have evolved into many forms in their thirty-year history. From the traditional pen-and-paper form, that originated with Dungeons & Dragons, with a group of friends playing around a table, to large live-action role-playing game, with hundreds of people acting out their assumed roles. The first computer role-playing games appeared over twenty-five years ago and massively multi-player role-playing games, such as World of Warcraft are now one of the most popular genres of digital games. Despite this diversity players at least seem to think they know when something is a role-playing game. When players, writers and game designers say “this is a role-playing game” there are no problems, they all seem to know what each other means, what is and is not a role-playing game. Yet there is no commonly accepted definition of the form. Understandable, perhaps, given the diversity, but the implicit agreement about its use means that there may well be some common underlying features shared by the various examples. Hampering any attempt to understand what makes a game a role-playing game is the subtle divide between role-playing and role-playing game. Role-playing can take in many places, not all of them games (such as ritual, social activities, therapy, etc). This means that definitions of the role-playing activity are not that useful in separating role-playing games from other games. In this paper we start from the position that the players are correct: they know what a role-playing game is. By examining a range of role-playing games some common features of them emerge. This results in a definition that is more successful than previous ones at identifying both what is, and what is not, a role-playing game.

Large Language Models (LLMs) have emerged as promising zero-shot rankers, but their performance is highly sensitive to prompt formulation. In particular, role-play prompts, where the model is assigned a functional role or identity, often give more robust and accurate relevance rankings. However, the mechanisms and diversity of role-play effects remain underexplored, limiting both effective use and interpretability. In this work, we systematically examine how role-play variations influence zero-shot LLM rankers. We employ causal intervention techniques from mechanistic interpretability to trace how role-play information shapes relevance judgments in LLMs. Our analysis reveals that (1) careful formulation of role descriptions have a large effect on the ranking quality of the LLM; (2) role-play signals are predominantly encoded in early layers and communicate with task instructions in middle layers, while receiving limited interaction with query or document representations. Specifically, we identify a group of attention heads that encode information critical for role-conditioned relevance. These findings not only shed light on the inner workings of role-play in LLM ranking but also offer guidance for designing more effective prompts in IR and beyond, pointing toward broader opportunities for leveraging role-play in zero-shot applications.