# Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing

arXiv: https://arxiv.org/abs/2409.16913 · HTML: https://mlsanity.com/paper/2409.16913/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 52 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 30 of 45)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [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)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://mlsanity.com/paper/2310.00746/) (2023)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [R-Tuning: Instructing Large Language Models to Say `I Don't Know'](https://mlsanity.com/paper/2311.09677/) (2023)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [LLM Internal States Reveal Hallucination Risk Faced With a Query](https://mlsanity.com/paper/2407.03282/) (2024)
- [Personalized Dialogue Generation with Diversified Traits](https://mlsanity.com/paper/1901.09672/) (2019)
- [Alignment for Honesty](https://mlsanity.com/paper/2312.07000/) (2023)
- [Aligning Large Language Models with Human Preferences through Representation Engineering](https://mlsanity.com/paper/2312.15997/) (2023)
- [Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback](https://mlsanity.com/paper/2403.18349/) (2024)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [DynaEval: Unifying Turn and Dialogue Level Evaluation](https://mlsanity.com/paper/2106.01112/) (2021)
- [ChatHaruhi: Reviving Anime Character in Reality via Large Language Model](https://mlsanity.com/paper/2308.09597/) (2023)
- [Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method](https://mlsanity.com/paper/2310.17918/) (2023)
- [Can AI Assistants Know What They Don't Know?](https://mlsanity.com/paper/2401.13275/) (2024)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)

## Built on by (most cited first, 3 of 3)

- [RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data](https://mlsanity.com/paper/2505.19030/) (2025)
- [How to Interpret Agent Behavior](https://mlsanity.com/paper/2605.13625/) (2026)
- [Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents](https://mlsanity.com/paper/2606.25632/) (2026)

## Abstract (arXiv)

Role-Playing Agents (RPAs) have shown remarkable performance in various applications, yet they often struggle to recognize and appropriately respond to hard queries that conflict with their role-play knowledge. To investigate RPAs' performance when faced with different types of conflicting requests, we develop an evaluation benchmark that includes contextual knowledge conflicting requests, parametric knowledge conflicting requests, and non-conflicting requests to assess RPAs' ability to identify conflicts and refuse to answer appropriately without over-refusing. Through extensive evaluation, we find that most RPAs behave significant performance gaps toward different conflict requests. To elucidate the reasons, we conduct an in-depth representation-level analysis of RPAs under various conflict scenarios. Our findings reveal the existence of rejection regions and direct response regions within the model's forwarding representation, and thus influence the RPA's final response behavior. Therefore, we introduce a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model's refusal accuracy. The experimental results validate the effectiveness of our editing method, improving RPAs' refusal ability of conflicting requests while maintaining their general role-playing capabilities.