Pith. sign in

REVIEW 3 cited by

LLM Roleplay: Simulating Human-Chatbot Interaction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.03974 v2 pith:K6MO3AAM submitted 2024-07-04 cs.CL

classification cs.CL
keywords dialogueshuman-chatbotmethodroleplayconductgenerategoalshigh
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective user studies can be prohibitively high and often only allow for a narrow analysis of specific dialogue goals and participant demographics. In this paper, we propose LLM Roleplay: a goal-oriented, persona-based method to automatically generate diverse multi-turn dialogues simulating human-chatbot interaction. LLM Roleplay can be applied to generate dialogues with any type of chatbot and uses large language models (LLMs) to play the role of textually described personas. To validate our method, we collect natural human-chatbot dialogues from different sociodemographic groups and conduct a user study to compare these with our generated dialogues. We evaluate the capabilities of state-of-the-art LLMs in maintaining a conversation during their embodiment of a specific persona and find that our method can simulate human-chatbot dialogues with a high indistinguishability rate.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles

    cs.CY 2025-07 conditional novelty 7.0 of 10

    A position paper contends that LLM agents, despite their human-like talk, are often too rich in detail to serve as scientific models, and proposes conditions where they still excel.

  2. ProfiLLM: An LLM-Based Framework for Implicit Profiling of Chatbot Users

    cs.AI 2025-06 conditional novelty 6.0 of 10

    ProfiLLM infers chatbot users' IT/cybersecurity proficiency from their prompts, achieving a rapid initial reduction in profiling error in synthetic and limited human evaluations.

  3. DialogueForge: LLM Simulation of Human-Chatbot Dialogue

    cs.CL 2025-07 conditional novelty 4.0 of 10

    DialogueForge generates synthetic human-chatbot dialogues by pitting an inquirer LLM against a responder LLM, and finds that fine-tuned small models can approach GPT-4o-level realism on LLM-judged metrics.

Pith tools