mlsanityData to 7 Oct 2026

Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?

arXiv 2305.15908 ↗First posted 25 May 2023cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events. In this paper, we study the task of response generation in LDs. We evaluate whether general-purpose Pre-trained Language Models (PLM) are appropriate for this purpose. We fine-tune two PLMs, GePpeTto (GPT-2) and iT5, using a dataset of LDs. We experiment with different representations of the personal knowledge extracted from LDs for grounded response generation, including the graph representation of the mentioned events and participants. We evaluate the performance of the models via automatic metrics and the contribution of the knowledge via the Integrated Gradients technique. We categorize the natural language generation errors via human evaluations of contextualization, appropriateness and engagement of the user.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

23 of 32 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  5. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  6. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  7. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  8. 2020Investigating Pretrained Language Models for Graph-to-Text Generationcited by 117
  9. 2020Knowledge-Grounded Dialogue Generation with Pre-trained Language Modelscited by 107
  10. 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 107
  11. 2019Personalizing Dialogue Agents via Meta-Learningcited by 83
  12. 2023Inseq: An Interpretability Toolkit for Sequence Generation Modelscited by 78
11 more
  1. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  2. 2022Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Counteringcited by 40
  3. 2022Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Studycited by 30
  4. 2017Personalization in Goal-Oriented Dialogcited by 28
  5. 2022Personalized Dialogue Generation with Persona-Adaptive Attentioncited by 24
  6. 2022IT5: Text-to-text Pretraining for Italian Language Understanding and Generationcited by 20
  7. 2020GePpeTto Carves Italian into a Language Modelcited by 16
  8. 2022Building a Personalized Dialogue System with Prompt-Tuningcited by 9
  9. 2023Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Functioncited by 7
  10. 2021Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Modelcited by 5
  11. 2019Look Who's Talking: Inferring Speaker Attributes from Personal Longitudinal Dialogcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 50
  2. 2024Are LLMs Robust for Spoken Dialogues?cited by 7
  3. 2024Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialoguecited by 7
  4. 2025AI-generated Text Detection: A Multifaceted Approach to Binary and Multiclass Classificationcited by 3
  5. 2025Post Persona Alignment for Multi-Session Dialogue Generationcited by 3
  6. 2024Personalized LLM for Generating Customized Responses to the Same Query from Different Userscited by 1