mlsanityData to 14 Oct 2026

Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters

arXiv 2211.06869 ↗First posted 13 Nov 2022cs.CL cs.AIcited by 16

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series and is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes. These extensive annotations may empower LLMs to unlock character-driven dialogue capabilities. Furthermore, it can serve as a universal benchmark for evaluating how well can a LLM aligning with a specific character. We benchmark LLMs on HPD using both fine-tuning and in-context learning settings. Evaluation results reveal that although there is substantial room for improvement in generating high-quality, character-aligned responses, the proposed dataset is valuable in guiding models toward responses that better align with the character of Harry Potter.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 17 of its 32 references that are in the map. First posted on arXiv 13 Nov 2022.

Builds on

17 of 32 references.

References · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  4. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  5. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  6. 2016A Persona-Based Neural Conversation Modelcited by 223
  7. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  8. 2019Personalized Dialogue Generation with Diversified Traitscited by 74
  9. 2019A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Datacited by 74
  10. 2021Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answeringcited by 39
  11. 2020Towards Data Distillation for End-to-end Spoken Conversational Question Answeringcited by 35
  12. 2021Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledgecited by 30
5 more
  1. 2021Self-supervised Dialogue Learning for Spoken Conversational Question Answeringcited by 28
  2. 2020Pchatbot: A Large-Scale Dataset for Personalized Chatbotcited by 26
  3. 2020Profile Consistency Identification for Open-domain Dialogue Agentscited by 22
  4. 2022COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personascited by 20
  5. 2017Neural Personalized Response Generation as Domain Adaptationcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 3; 2026: 3.

16 papers.

Sort:

By area:

  1. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  2. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 97
  3. 2023Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observationscited by 59
  4. 2024BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Datacited by 50
  5. 2023Interactive Natural Language Processingcited by 31
  6. 2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27
  7. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
  8. 2024Mitigating Hallucination in Fictional Character Role-Playcited by 18
  9. 2023From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Promptingcited by 10
  10. 2025CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewardscited by 6
  11. 2024Characteristic AI Agents via Large Language Modelscited by 5
  12. 2026ActorMind: Emulating Human Actor Reasoning for Speech Role-Playingcited by 4
4 more
  1. 2026PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Modelscited by 3
  2. 2025Learning a Single Token to Replace Long System Prompts in LLMscited by 2
  3. 2023Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehensioncited by 1
  4. 2026TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation
  2. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment
  3. 2024BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model
  4. 2026Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning
  5. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
  6. 2024DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents
  7. 2024A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Styles
  8. 2023RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models