Lune

EMNLP Findings2023

Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues

Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Abstract

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple knowledge sources selection and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources.

To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal Jungle cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications cites LoRA: Low-Rank Adaptation of Large Language Models
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Toolformer: Language Models Can Teach Themselves to Use Tools
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory GraphsZheng Wang, Zhongyang Li, Zeren Jiang, Dandan Tu et al.EMNLP 2024 · 6 citations
  2. PANDA: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language ModelsJinsung Kim, Seonmin Koo, Heuiseok LimEMNLP 2024 · 2 citations
  3. AppBench: Planning of Multiple APIs from Various APPs for Complex User InstructionHongru Wang, Rui Wang, Boyang Xue, Heming Xia et al.EMNLP 2024 · 2 citations
  4. From an LLM Swarm to a PDDL-empowered Hive: Planning Self-executed Instructions in a Multi-modal JungleKaustubh Vyas, Damien Graux, Yijun Yang, Sébastien Montella et al.ICLR 2025
  5. Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical ApplicationsZhe Chen, Yusheng Liao, Shuyang Jiang, Pingjie Wang et al.ACL 2025

Builds on32

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  3. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  4. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging FaceYongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li et al.NeurIPS 2023 · 1,778 citations
  5. Beyond Goldfish Memory: Long-Term Open-Domain ConversationJing Xu, Arthur Szlam, Jason WestonACL 2022 · 329 citations

Related papers

  1. Multi-Source Multi-Type Knowledge Exploration and Exploitation for Dialogue GenerationXuanfan Ni, Hongliang Dai, Zhaochun Ren, Piji LiEMNLP 2023 · 1 citation
  2. Pretrained Language Models for Dialogue Generation with Multiple Input SourcesYu Cao, Wei Bi, Meng Fang, Dacheng TaoEMNLP Findings 2020 · 24 citations
  3. Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao et al.EMNLP 2020 · 153 citations
  4. KPT: Keyword-Guided Pre-training for Grounded Dialog GenerationQi Zhu, Fei Mi, Zheng Zhang, Yasheng Wang et al.AAAI 2023 · 5 citations
  5. Call for Customized Conversation: Customized Conversation Grounding Persona and KnowledgeYoonna Jang, Jungwoo Lim, Yuna Hur, Dongsuk Oh et al.AAAI 2022 · 47 citations
Dusk over the sea between two cliffs drawn in fine vertical lines