paper-with-me

Papers

K-PERM: Personalized Response Generation Using Dynamic Knowledge Retrieval and Persona-Adaptive Queries

2023-12-29 · Kanak Raj, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayanan, Manas Gaur

Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to appropriately tend to a user's persona. This is particularly crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response with supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. K-PERM achieves state-of-the-art performance on the popular FoCus dataset, containing real-world personalized conversations concerning global landmarks. We show that using responses from K-PERM can improve performance in state-of-the-art LLMs (GPT 3.5) by 10.5%, highlighting the impact of K-PERM for personalizing chatbots.

📄 PDF Abstract BibTeX arXiv:2312.17748

Code (1)

kanak8278/dialogkperm 공식 구현 pytorch

Tasks

NutritionResponse GenerationRetrieval

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems

2024-01-24 · Hongru Wang, WenYu Huang, Yang Deng, Rui Wang 외

Large Language Models (LLMs) has shown exceptional capabilities in many natual language understanding and generation tasks. However, the personalization issue still remains a much-coveted property, especially when it com…

RAGResponse GenerationRetrievalRetrieval-augmented Generation

Personalized LLM Response Generation with Parameterized Memory Injection

2024-04-04 · Kai Zhang, Yejin Kim, Xiaozhong Liu

Large Language Models (LLMs) have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, personalized LLM response generation holds the potential to offer substantial benefi…

Bayesian Optimisationparameter-efficient fine-tuningResponse Generation

TutorLLM: Customizing Learning Recommendations with Knowledge Tracing and Retrieval-Augmented Generation

2025-01-20 · Zhaoxing Li, Vahid Yazdanpanah, Jindi Wang, Wen Gu 외

The integration of AI in education offers significant potential to enhance learning efficiency. Large Language Models (LLMs), such as ChatGPT, Gemini, and Llama, allow students to query a wide range of topics, providing …

Knowledge TracingRAGRetrievalRetrieval-augmented Generation

Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment

2025-06-12 · Hongda Sun, Jiaren Peng, Wenzhong Yang, Liang He 외

Medical dialogue systems (MDS) have emerged as crucial online platforms for enabling multi-turn, context-aware conversations with patients. However, existing MDS often struggle to (1) identify relevant medical knowledge …

Dialogue GenerationTriplet

Bilateral Personalized Dialogue Generation with Contrastive Learning

2021-06-15 · Bin Li, Hanjun Deng

Generating personalized responses is one of the major challenges in natural human-robot interaction. Current researches in this field mainly focus on generating responses consistent with the robot's pre-assigned persona,…

Contrastive LearningDialogue GenerationLanguage ModellingTransfer Learning