# Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing

arXiv: https://arxiv.org/abs/2409.11726 · HTML: https://mlsanity.com/paper/2409.11726/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 56 references that are in the map.
- First posted on arXiv 18 Sep 2024.

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [Wider and Deeper LLM Networks are Fairer LLM Evaluators](https://mlsanity.com/paper/2308.01862/) (2023)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent](https://mlsanity.com/paper/2402.13717/) (2024)
- [From Role-Play to Drama-Interaction: An LLM Solution](https://mlsanity.com/paper/2405.14231/) (2024)
- [Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works](https://mlsanity.com/paper/2404.12726/) (2024)
- [IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation](https://mlsanity.com/paper/2407.01093/) (2024)
- [PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning](https://mlsanity.com/paper/2405.02501/) (2024)
- [Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots](https://mlsanity.com/paper/2403.03307/) (2024)
- [Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior](https://mlsanity.com/paper/2407.02099/) (2024)
- [Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers](https://mlsanity.com/paper/2403.01061/) (2024)
- [Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignment](https://mlsanity.com/paper/2406.13934/) (2024)

## Built on by (most cited first, 9 of 9)

- [Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?](https://mlsanity.com/paper/2410.23426/) (2024)
- [ExpSeek: Self-Triggered Experience Seeking for Web Agents](https://mlsanity.com/paper/2601.08605/) (2026)
- [SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents](https://mlsanity.com/paper/2502.15538/) (2025)
- [Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization](https://mlsanity.com/paper/2503.17928/) (2025)
- [ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing](https://mlsanity.com/paper/2604.11103/) (2026)
- [Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects](https://mlsanity.com/paper/2603.03915/) (2026)
- [Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information](https://mlsanity.com/paper/2604.15701/) (2026)
- [Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes](https://mlsanity.com/paper/2601.04716/) (2026)
- [CHARM: Character Hallucination for Multicultural Role Play Benchmark](https://mlsanity.com/paper/2609.01352/) (2026)

## Abstract (arXiv)

Large language model (LLM) role-playing has gained widespread attention. Authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose RoleKE-Bench to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to detect these two types of errors effectively, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S2RD), to explore further the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.