mlsanityData to 14 Oct 2026

Making a Long Story Short in Conversation Modeling

arXiv 2402.00143 ↗First posted 31 Jan 2024cs.CL cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Conversation systems accommodate diverse users with unique personalities and distinct writing styles. Within the domain of multi-turn dialogue modeling, this work studies the impact of varied utterance lengths on the quality of subsequent responses generated by conversation models. Using GPT-3 as the base model, multiple dialogue datasets, and several metrics, we conduct a thorough exploration of this aspect of conversational models. Our analysis sheds light on the complex relationship between utterance lengths and the quality of follow-up responses generated by dialogue systems. Empirical findings suggests that, for certain types of conversations, utterance lengths can be reduced by up to 72% without any noticeable difference in the quality of follow-up responses.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 31 Jan 2024.

Builds on

21 of 30 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  6. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  7. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 198
  8. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  9. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
  10. 2023Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversationscited by 89
  11. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  12. 2022The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialoguescited by 79
9 more
  1. 2019Improving Multi-turn Dialogue Modelling with Utterance ReWritercited by 58
  2. 2021TIMEDIAL: Temporal Commonsense Reasoning in Dialogcited by 55
  3. 2020Incomplete Utterance Rewriting as Semantic Segmentationcited by 33
  4. 2021Commonsense-Focused Dialogues for Response Generation: An Empirical Studycited by 30
  5. 2022GPT-3-driven pedagogical agents for training children's curious question-asking skillscited by 29
  6. 2023The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answeringcited by 26
  7. 2022Exploring The Design of Prompts For Applying GPT-3 based Chatbots: A Mental Wellbeing Case Study on Mechanical Turkcited by 13
  8. 2022Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generationcited by 9
  9. 2023Ericson: An Interactive Open-Domain Conversational Search Agentcited by 1

Built on by

Not cited yet.