Abstract
Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks. In complex application scenarios, users tend to engage in multi-turn conversations with ChatGPT to keep contextual information and obtain comprehensive responses. However, human forgetting and model contextual forgetting remain prominent issues in multi-turn conversation scenarios, which challenge the users’ conversation comprehension and contextual continuity for ChatGPT. To address these challenges, we propose an interactive conversation visualization system called C5, which includes Global View, Topic View, and Context-associated Q&A View. The Global View uses the GitLog diagram metaphor to represent the conversation structure, presenting the trend of conversation evolution and supporting the exploration of locally salient features. The Topic View is designed to display all the question and answer nodes and their relationships within a topic using the structure of a knowledge graph, thereby display the relevance and evolution of conversations. The Context-associated Q&A View consists of three linked views, which allow users to explore individual conversations deeply while providing specific contextual information when posing questions. The usefulness and effectiveness of C5 were evaluated through a case study and a user study.
Graphical abstract
Similar content being viewed by others
References
Ahuja K, Hada R, Ochieng M, Jain P, Diddee H, Maina S, Ganu T, Segal S, Axmed M, Bali K et al (2023) Mega: Multilingual evaluation of generative ai. arXiv preprint arXiv:2303.12528
Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3(Jan):993–1022
Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H (eds) Proceedings of advances in neural information processing systems, vol 33. Curran Associates Inc, New York, pp 1877–1901
Cao Z, Li S, Liu Y, Li W, Ji H (2015) A novel neural topic model and its supervised extension. In: Proceedings of the AAAI conference on artificial intelligence, vol 29(1)
Castronovo S, Frey J, Poller P (2008) A generic layout-tool for summaries of meetings in a constraint-based approach. In: Machine learning for multimodal interaction: 5th international workshop, MLMI 2008, Utrecht, The Netherlands, September 8–10, 2008. Proceedings 5, Springer, pp 248–259 (2008)
Chang B, Sun G, Li T, Huang H, Liang R (2023) MUSE: visual analysis of musical semantic sequence. IEEE Trans Vis Comput Gr 29(9):4015–4030. https://doi.org/10.1109/TVCG.2022.3175364
Cowell AJ, Gregory ML, Bruce J, Haack J, Love D, Rose S, Andrew AH (2006) Understanding the dynamics of collaborative multi-party discourse. Inf Vis 5(4):250–259
Cui W, Liu S, Tan L, Shi C, Song Y, Gao Z, Qu H, Tong X (2011) TextFlow: towards Better Understanding of Evolving Topics in Text. IEEE Trans Vis Comput Gr 17(12):2412–2421
Cui W, Liu S, Wu Z, Wei H (2014) How hierarchical topics evolve in large text corpora. IEEE Trans Vis Comput Gr 20(12):2281–2290
Cui Y, Li C, Chen C, Liang Y, Hu Y, Wang C (2021) VineMap: a metaphor visualization method for public opinion hierarchy from text data. J Vis 24(5):1097–1111
Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding, , pp 4171–4186. arXiv:1810.04805
Dhillon IS, Modha DS (2001) Concept decompositions for large sparse text data using clustering. Mach Learn 42(1–2):143–175
Dieng AB, Wang C, Gao J, Paisley J (2016) TopicRNN: a recurrent neural network with long-range semantic dependency. arXiv e-prints arXiv:1611.01702
Ehlen P, Purver M, Niekrasz J, Lee K, Peters S (2008) Meeting adjourned: off-line learning interfaces for automatic meeting understanding. In: Proceedings of the 13th international conference on Intelligent user interfaces, pp 276–284
El-Assady M, Gold V, Acevedo C, Collins C, Keim D (2016) ConToVi: multi-party conversation exploration using topic-space views. In: Computer graphics forum, vol 35. Wiley Online Library, pp 431–440
El-Assady M, Sevastjanova R, Gipp B, Keim D, Collins C (2017) NEREx: named-entity relationship exploration in multi-party conversations. In: Computer graphics forum, vol 36. Wiley Online Library, pp 213–225 (2017)
Floridi L, Chiriatti M (2020) GPT-3: its nature, scope, limits, and consequences. Mind Mach 30:681–694
Fujiwara T, Malakar P, Reda K, Vishwanath V, Papka ME, Ma KL (2017) A visual analytics system for optimizing communications in massively parallel applications. In: Proceedings of IEEE conference on visual analytics science and technology, IEEE, pp 59–70
Havre S, Hetzler E, Whitney P, Nowell L (2002) ThemeRiver: visualizing thematic changes in large document collections. IEEE Trans Vis Comput Gr 8(1):9–20
Hendy A, Abdelrehim M, Sharaf A, Raunak V, Gabr M, Matsushita H, Kim YJ, Afify M, Awadalla HH (2023) How good are GPT models at machine translation? a comprehensive evaluation. arXiv preprint arXiv:2302.09210
Jacobsen B, Wallinger M, Kobourov S, Nöllenburg M (2020) MetroSets: visualizing sets as metro maps. IEEE Trans Vis Comput Gr 27(2):1257–1267
Jiao W, Wang W, Huang J, Wang X, Tu Z (2023) Is ChatGPT a good translator. A preliminary study. arXiv:2301.08745
Katharopoulos A, Vyas A, Pappas N, Fleuret F (2020) Transformers are RNNs: fast autoregressive transformers with linear attention. In: Proceedings of the 37th international conference on machine learning, vol 119. PMLR, pp 5156–5165
Kieffer S, Dwyer T, Marriott K, Wybrow M (2016) HOLA: human-like orthogonal network layout. IEEE Trans Vis Comput Gr 22(1):349–358
Kim M, Kang K, Park D, Choo J, Elmqvist N (2016) TopicLens: efficient multi-level visual topic exploration of large-scale document collections. IEEE Trans Vis Comput Graphics 23(1):151–160
Knittel J, Koch S, Tang T, Chen W, Wu Y, Liu S, Ertl T (2022) Real-time visual analysis of high-volume social media posts. IEEE Trans Vis Comput Gr 28(1):879–889
Lai VD, Ngo NT, Veyseh APB, Man H, Dernoncourt F, Bui T, Nguyen TH (2023) ChatGPT beyond english: towards a comprehensive evaluation of large language models in multilingual learning. arXiv preprint arXiv:2304.05613
Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the international conference on machine learning, vol 32. PMLR, pp 1188–1196
Lee D, Seung HS (2000) Algorithms for non-negative matrix factorization. In: Proceedings of advances in neural information processing systems, vol 13
Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the annual meeting of the association for computational linguistics, pp 7871–7880
Li Y (2023) Unlocking context constraints of LLMs: enhancing context efficiency of LLMs with self-information-based content filtering. arXiv preprint arXiv:2304.12102
Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2023) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput Surv 55(9):1–35
Liu S, Wu Y, Wei E, Liu M, Liu Y (2013) StoryFlow: tracking the Evolution of Stories. IEEE Trans Vis Comput Gr 19(12):2436–2445
Liu S, Yin J, Wang X, Cui W, Cao K, Pei J (2016) Online visual analytics of text streams. IEEE Trans Vis Comput Gr 22(11):2451–2466
Liu Y, Han T, Ma S, Zhang J, Yang Y, Tian J, He H, Li A, He M, Liu Z et al (2023) Summary of ChatGPT/GPT-4 research and perspective towards the future of large language models. arXiv preprint arXiv:2304.01852
Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692
Loiola EM, De Abreu NMM, Boaventura-Netto PO, Hahn P, Querido T (2007) A survey for the quadratic assignment problem. Eur J Oper Res 176(2):657–690
Madaan A, Tandon N, Clark P, Yang Y (2022) Memory-assisted prompt editing to improve GPT-3 after deployment. arXiv preprint arXiv:2201.06009
Madaan A, Tandon N, Gupta P, Hallinan S, Gao L, Wiegreffe S, Alon U, Dziri N, Prabhumoye S, Yang Y et al (2023) Self-Refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651 (2023)
Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781
Niu Z, Zhong G, Yu H (2021) A review on the attention mechanism of deep learning. Neurocomputing 452:48–62
OpenAI: Gpt-4 technical report. arXiv e-prints arXiv:2303.08774 (2023)
Peng Y, Fan X, Chen R, Yu Z, Liu S, Chen Y, Zhao Y, Zhou F (2023) Visual abstraction of dynamic network via improved multi-class blue noise sampling. Front Comput Sci 17(1):171701
Pennington J, Socher R, Manning CD (2014) GloVe: global vectors for word representation. In: Proceedings of the conference on empirical methods in natural language processing, pp 1532–1543
Radford A, Narasimhan K, Salimans T, Sutskever I et al (2018) Improving language understanding by generative pre-training
Savelka J, Agarwal A, Bogart C, Song Y, Sakr M (2023) Can generative pre-trained transformers (GPT) pass assessments in higher education programming courses? arXiv preprint arXiv:2303.09325
Shi Y, Bryan C, Bhamidipati S, Zhao Y, Zhang Y, Ma KL (2018) MeetingVis: visual narratives to assist in recalling meeting context and content. IEEE Trans Vis Comput Gr 24(6):1918–1929
Shi Y, Wang Y, Qi Y, Chen J, Xu X, Ma KL (2017) IdeaWall: improving creative collaboration through combinatorial visual stimuli. In: Proceedings of the 2017 ACM conference on computer supported cooperative work and social computing, pp 594–603
Shneiderman B (1996) The eyes have it: a task by data type taxonomy for information visualizations. In: Proceedings of IEEE symposium on visual languages, IEEE, pp 336–343
Sun G, Wu Y, Liu S, Peng TQ, Zhu JJ, Liang R (2014) EvoRiver: visual analysis of topic coopetition on social media. IEEE Trans Vis Comput Gr 20(12):1753–1762
Sun G, Zhu Z, Zhang G, Xu C, Wang Y, Zhu S, Chang B, Liang R (2023) Application of mathematical optimization in data visualization and visual analytics: a survey. IEEE Transactions on Big Data. Early Access
Sun G, Zhu Z, Zhang G, Xu C, Wang Y, Zhu S, Chang B, Liang R (2023) Application of mathematical optimization in data visualization and visual analytics: a survey. IEEE Trans Big Data. https://doi.org/10.1109/TBDATA.2023.3262151
Tafjord O, Mishra BD, Clark P (2022) Entailer: answering questions with faithful and truthful chains of reasoning. arXiv preprint arXiv:2210.12217
Tanahashi Y, Ma KL (2012) Design considerations for optimizing storyline visualizations. IEEE Trans Vis Comput Gr 18(12):2679–2688
Wang Y, Sun G, Zhu Z, Li T, Chen L, Liang R (2024) E2 storyline: visualizing the relationship with triplet entities and event discovery. ACM Trans Intell Syst Technol 15(1):1–26
Wei J, Tay Y, Bommasani R, Raffel C, Zoph B, Borgeaud S, Yogatama D, Bosma M, Zhou D, Metzler D et al (2022) Emergent abilities of large language models. arXiv preprint arXiv:2206.07682
Wu Y, Chen Z, Sun G, Xie X, Cao N, Liu S, Cui W (2018) StreamExplorer: a multi-stage system for visually exploring events in social streams. IEEE Trans Visual Comput Gr 24(10):2758–2772
Yang X, Li Y, Zhang X, Chen H, Cheng W (2023) Exploring the limits of ChatGPT for query or aspect-based text summarization. arXiv preprint arXiv:2302.08081
Zhou F, Mi J, Zhang B, Shi J, Zhang R, Chen X, Zhao Y, Zhang J (2023) Reliable knowledge graph fact prediction via reinforcement learning. Vis Comput Ind Biomed Art 6(1):21
Zhu S, Shen Y, Zhu Z, Xia W, Chang B, Liang R, Sun G (2022) VAC\(^2\): visual analysis of combined causality in event sequences. arXiv preprint arXiv:2206.05420
Zhu Z, Shen Y, Zhu S, Zhang G, Liang R, Sun G (2023) Towards better pattern enhancement in temporal evolving set visualization. J Vis 26(3):611–629
Acknowledgements
This work is supported by Zhejiang Provincial Natural Science Foundation of China (LR23F020003 and LTGG23F020005) and National Natural Science Foundation of China (62372411 and 62036009). Furthermore, thanks to the participants for taking part in the requirement analysis and evaluation. Guodao Sun is the corresponding author.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Supplementary file1 (MP4 17454 KB)
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liang, P., Ye, D., Zhu, Z. et al. C5: toward better conversation comprehension and contextual continuity for ChatGPT. J Vis 27, 713–730 (2024). https://doi.org/10.1007/s12650-024-00980-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12650-024-00980-4