# From Guessing to Asking: An Approach to Resolving the Persona Knowledge Gap in LLMs during Multi-Turn Conversations

arXiv: https://arxiv.org/abs/2503.12556 · HTML: https://mlsanity.com/paper/2503.12556/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [NUBIA: NeUral Based Interchangeability Assessor for Text Generation](https://mlsanity.com/paper/2004.14667/) (2020)
- [Implicit Personalization in Language Models: A Systematic Study](https://mlsanity.com/paper/2405.14808/) (2024)
- [MedInsight: A Multi-Source Context Augmentation Framework for Generating Patient-Centric Medical Responses using Large Language Models](https://mlsanity.com/paper/2403.08607/) (2024)
- [K-PERM: Personalized Response Generation Using Dynamic Knowledge Retrieval and Persona-Adaptive Queries](https://mlsanity.com/paper/2312.17748/) (2023)
- [ExpressivityBench: Can LLMs Communicate Implicitly?](https://mlsanity.com/paper/2411.08010/) (2024)
- [Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing](https://mlsanity.com/paper/2004.03755/) (2020)
- [Improving Items and Contexts Understanding with Descriptive Graph for Conversational Recommendation](https://mlsanity.com/paper/2304.09093/) (2023)

## Built on by (most cited first, 1 of 1)

- [Can LLMs Generate High-Quality Task-Specific Conversations?](https://mlsanity.com/paper/2508.02931/) (2025)

## Abstract (arXiv)

In multi-turn dialogues, large language models (LLM) face a critical challenge of ensuring coherence while adapting to user-specific information. This study introduces the persona knowledge gap, the discrepancy between a model's internal understanding and the knowledge required for coherent, personalized conversations. While prior research has recognized these gaps, computational methods for their identification and resolution remain underexplored. We propose Conversation Preference Elicitation and Recommendation (CPER), a novel framework that dynamically detects and resolves persona knowledge gaps using intrinsic uncertainty quantification and feedback-driven refinement. CPER consists of three key modules: a Contextual Understanding Module for preference extraction, a Dynamic Feedback Module for measuring uncertainty and refining persona alignment, and a Persona-Driven Response Generation module for adapting responses based on accumulated user context. We evaluate CPER on two real-world datasets: CCPE-M for preferential movie recommendations and ESConv for mental health support. Using A/B testing, human evaluators preferred CPER's responses 42% more often than baseline models in CCPE-M and 27% more often in ESConv. A qualitative human evaluation confirms that CPER's responses are preferred for maintaining contextual relevance and coherence, particularly in longer (12+ turn) conversations.