# Learning Retrieval Augmentation for Personalized Dialogue Generation

arXiv: https://arxiv.org/abs/2406.18847 · HTML: https://mlsanity.com/paper/2406.18847/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents](https://mlsanity.com/paper/1901.08149/) (2019)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [You Impress Me: Dialogue Generation via Mutual Persona Perception](https://mlsanity.com/paper/2004.05388/) (2020)
- [BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data](https://mlsanity.com/paper/2106.06169/) (2021)
- [Low-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2002.10348/) (2020)
- [Incremental Transformer with Deliberation Decoder for Document Grounded Conversations](https://mlsanity.com/paper/1907.08854/) (2019)
- [A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation](https://mlsanity.com/paper/2204.09867/) (2022)
- [Personalized Dialogue Generation with Persona-Adaptive Attention](https://mlsanity.com/paper/2210.15088/) (2022)

## Built on by (most cited first, 18 of 18)

- [A Survey of Personalization: From RAG to Agent](https://mlsanity.com/paper/2504.10147/) (2025)
- [On the Way to LLM Personalization: Learning to Remember User Conversations](https://mlsanity.com/paper/2411.13405/) (2024)
- [PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues](https://mlsanity.com/paper/2502.21017/) (2025)
- [AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2409.01579/) (2024)
- [Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models](https://mlsanity.com/paper/2505.17051/) (2025)
- [MAP: Multi-user Personalization with Collaborative LLM-powered Agents](https://mlsanity.com/paper/2503.12757/) (2025)
- [Automated Privacy Information Annotation in Large Language Model Interactions](https://mlsanity.com/paper/2505.20910/) (2025)
- [Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations](https://mlsanity.com/paper/2412.11250/) (2024)
- [Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.02993/) (2026)
- [Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2505.21907/) (2025)
- [Personalized LLM for Generating Customized Responses to the Same Query from Different Users](https://mlsanity.com/paper/2412.11736/) (2024)
- [Score Before You Speak: Improving Persona Consistency in Dialogue Generation using Response Quality Scores](https://mlsanity.com/paper/2508.06886/) (2025)
- [Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods](https://mlsanity.com/paper/2510.20252/) (2025)
- [Embedding-Based Context-Aware Reranker](https://mlsanity.com/paper/2510.13329/) (2025)
- [One Instruction Does Not Fit All: How Well Do Embeddings Align Personas and Instructions in Low-Resource Indian Languages?](https://mlsanity.com/paper/2601.10205/) (2026)
- [An Annotation Scheme and Classifier for Personal Facts in Dialogue](https://mlsanity.com/paper/2605.10339/) (2026)
- [User-Aware Active Knowledge Acquisition for Emotional Support Dialogue](https://mlsanity.com/paper/2605.29715/) (2026)
- [SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice](https://mlsanity.com/paper/2606.04155/) (2026)

## Abstract (arXiv)

Personalized dialogue generation, focusing on generating highly tailored responses by leveraging persona profiles and dialogue context, has gained significant attention in conversational AI applications. However, persona profiles, a prevalent setting in current personalized dialogue datasets, typically composed of merely four to five sentences, may not offer comprehensive descriptions of the persona about the agent, posing a challenge to generate truly personalized dialogues. To handle this problem, we propose Learning Retrieval Augmentation for Personalized DialOgue Generation (LAPDOG), which studies the potential of leveraging external knowledge for persona dialogue generation. Specifically, the proposed LAPDOG model consists of a story retriever and a dialogue generator. The story retriever uses a given persona profile as queries to retrieve relevant information from the story document, which serves as a supplementary context to augment the persona profile. The dialogue generator utilizes both the dialogue history and the augmented persona profile to generate personalized responses. For optimization, we adopt a joint training framework that collaboratively learns the story retriever and dialogue generator, where the story retriever is optimized towards desired ultimate metrics (e.g., BLEU) to retrieve content for the dialogue generator to generate personalized responses. Experiments conducted on the CONVAI2 dataset with ROCStory as a supplementary data source show that the proposed LAPDOG method substantially outperforms the baselines, indicating the effectiveness of the proposed method. The LAPDOG model code is publicly available for further exploration. https://github.com/hqsiswiliam/LAPDOG