2000 character limit reached
Making a Long Story Short in Conversation Modeling (2402.00143v1)
Published 31 Jan 2024 in cs.CL and cs.HC
Abstract: 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.
- Gpt-3-driven pedagogical agents to train children’s curious question-asking skills. International Journal of Artificial Intelligence in Education.
- Cognitive network science reveals bias in gpt-3, gpt-3.5 turbo, and gpt-4 mirroring math anxiety in high-school students. Big Data and Cognitive Computing, 7(3).
- Controlling the intelligibility of referring expressions in dialogue. Journal of memory and language, 42(1):1–22.
- Allan Bell. 1984. Language style as audience design. Language in society, 13(2):145–204.
- Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
- Frugalgpt: How to use large language models while reducing cost and improving performance.
- The dangers of trusting stochastic parrots: Faithfulness and trust in open-domain conversational question answering.
- Michael Denkowski and Alon Lavie. 2014. Meteor universal: Language specific translation evaluation for any target language. In Proceedings of the ninth workshop on statistical machine translation, pages 376–380.
- BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
- MEEP: Is this engaging? prompting large language models for dialogue evaluation in multilingual settings. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2078–2100, Singapore. Association for Computational Linguistics.
- Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations. In Proc. Interspeech 2019, pages 1891–1895.
- News summarization and evaluation in the era of gpt-3.
- Enhance incomplete utterance restoration by joint learning token extraction and text generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3149–3158, Seattle, United States. Association for Computational Linguistics.
- Cassandra L Jacobs and Maryellen C MacDonald. 2023. A chimpanzee by any other name: The contributions of utterance context and information density on word choice. Cognition, 230:105265.
- Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression.
- Katikapalli Subramanyam Kalyan. 2023. A survey of gpt-3 family large language models including chatgpt and gpt-4.
- Prosocialdialog: A prosocial backbone for conversational agents. In EMNLP.
- Exploring the design of prompts for applying gpt-3 based chatbots: A mental wellbeing case study on mechanical turk. arXiv preprint arXiv:2209.11344.
- Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
- Incomplete utterance rewriting as semantic segmentation. arXiv preprint arXiv:2009.13166.
- G-eval: Nlg evaluation using gpt-4 with better human alignment.
- The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems.
- Athena 2.0: Discourse and user modeling in open domain dialogue.
- TIMEDIAL: Temporal commonsense reasoning in dialog. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7066–7076, Online. Association for Computational Linguistics.
- Chatgpt: Optimizing language models for dialogue.
- Blenderbot 3: a deployed conversational agent that continually learns to responsibly engage. arXiv preprint arXiv:2208.03188.
- Improving multi-turn dialogue modelling with utterance rewriter. arXiv preprint arXiv:1906.07004.
- Anaïs Tack and Chris Piech. 2022. The ai teacher test: Measuring the pedagogical ability of blender and gpt-3 in educational dialogues. arXiv preprint arXiv:2205.07540.
- Caroline Tagg and Philip Seargeant. 2014. Audience design and language choice in the construction and maintenance of translocal communities on social network sites. In The language of social media, pages 161–185. Springer.
- Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239.
- Lei Wang and Ee-Peng Lim. 2023. Zero-shot next-item recommendation using large pretrained language models. arXiv preprint arXiv:2304.03153.
- Ericson: An interactive open-domain conversational search agent. arXiv preprint arXiv:2304.02233.
- Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations.
- Commonsense-focused dialogues for response generation: An empirical study. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, Singapore and Online. Association for Computational Linguistics.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.