{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:02:52Z","timestamp":1775577772898,"version":"3.50.1"},"reference-count":34,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T00:00:00Z","timestamp":1701129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>This paper provides a pioneering examination and enhancement of generative chat models, with a specific focus on the BlenderBot 3 model. Through meticulous interaction with a diverse set of human participants, we dissected the fundamental components of these models, unveiling several deficiencies, including long-term memory and entity recognition. Leveraging these insights, we engineered refined, streamlined iterations, culminating in a chatbot that transcends the capabilities of all existing models. Our work follows Occam\u2019s razor principle and proves that, for tasks with relatively low complexity, using large overparameterized models instead of smaller ones does not bring significant benefits but increases latency, which may result in a lowered overall user experience. In upholding our commitment to transparency and the progression of shared knowledge, we have made our improved model universally accessible through open-source distribution.<\/jats:p>","DOI":"10.3390\/fi15120384","type":"journal-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T07:40:01Z","timestamp":1701157201000},"page":"384","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancements in BlenderBot 3: Expanding Beyond a Singular Model Governance and Boosting Generational Performance"],"prefix":"10.3390","volume":"15","author":[{"given":"Ondrej","family":"Kobza","sequence":"first","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1861-3778","authenticated-orcid":false,"given":"David","family":"Herel","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Cuhel","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tommaso","family":"Gargiani","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8401-4535","authenticated-orcid":false,"given":"Jan","family":"Pichl","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petr","family":"Marek","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakub","family":"Konrad","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Sedivy","sequence":"additional","affiliation":[{"name":"Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, 156 00 Prague, Czech Republic"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,28]]},"reference":[{"key":"ref_1","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., and Askell, A. (2020). Language Models are Few-Shot Learners. arXiv."},{"key":"ref_2","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., and Ray, A. (2022). Training language models to follow instructions with human feedback. arXiv."},{"key":"ref_3","unstructured":"OpenAI (2023). GPT-4 Technical Report. arXiv."},{"key":"ref_4","unstructured":"Shuster, K., Xu, J., Komeili, M., Ju, D., Smith, E.M., Roller, S., Ung, M., Chen, M., Arora, K., and Lane, J. (2022). BlenderBot 3: A deployed conversational agent that continually learns to responsibly engage. arXiv."},{"key":"ref_5","unstructured":"University of California, and Barbara, S. GauchoChat: Towards Proactive, Controllable, and Personalized Social Conversation. Proceedings of the Alexa Prize SocialBot Grand Challenge 5 Proceedings, Available online: https:\/\/www.amazon.science\/alexa-prize\/proceedings\/gauchochat-towards-proactive-controllable-and-personalized-social-conversation."},{"key":"ref_6","unstructured":"Stevens Institute of Technology From Hybrid Dialogers to Neural Responders. Proceedings of the Alexa Prize SocialBot Grand Challenge 5 Proceedings, Available online: https:\/\/www.amazon.science\/alexa-prize\/proceedings\/nam-from-hybrid-dialogers-to-neural-responders."},{"key":"ref_7","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., and Azhar, F. (2023). LLaMA: Open and Efficient Foundation Language Models. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Shuster, K., and Smith, E.M. (2020). Recipes for building an open-domain chatbot. arXiv.","DOI":"10.18653\/v1\/2021.eacl-main.24"},{"key":"ref_9","unstructured":"Muresan, S., Nakov, P., and Villavicencio, A. (2022, January 22\u201327). Internet-Augmented Dialogue Generation. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Izacard, G., and Grave, E. (2021). Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. arXiv.","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref_11","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.t., and Rockt\u00e4schel, T. (2021). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., O\u011fuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., and Yih, W.t. (2020). Dense Passage Retrieval for Open-Domain Question Answering. arXiv.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xu, J., Szlam, A., and Weston, J. (2021). Beyond Goldfish Memory: Long-Term Open-Domain Conversation. arXiv.","DOI":"10.18653\/v1\/2022.acl-long.356"},{"key":"ref_14","unstructured":"Dinan, E., Roller, S., Shuster, K., Fan, A., Auli, M., and Weston, J. (2019). Wizard of Wikipedia: Knowledge-Powered Conversational agents. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., and Weston, J. (2021). Retrieval Augmentation Reduces Hallucination in Conversation. arXiv.","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of Hallucination in Natural Language Generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_17","unstructured":"Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., and Chen, Y. (2023). Siren\u2019s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv."},{"key":"ref_18","unstructured":"Lee, J., Shim, M., Son, S., Park, C., Kim, Y., and Lim, H. (2022). There is no rose without a thorn: Finding weaknesses on BlenderBot 2.0 in terms of Model, Data and User-Centric Approach. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shuster, K., Komeili, M., Adolphs, L., Roller, S., Szlam, A., and Weston, J. (2022). Language Models that Seek for Knowledge: Modular Search and Generation for Dialogue and Prompt Completion. arXiv.","DOI":"10.18653\/v1\/2022.findings-emnlp.27"},{"key":"ref_20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2023). Attention Is All You Need. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., and Zettlemoyer, L. (2019). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref_22","unstructured":"Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cappelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., and Launay, J. (2023). The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only. arXiv."},{"key":"ref_23","unstructured":"Stanford University Dialogue Distillery: Crafting Interpolable, Interpretable, and Introspectable Dialogue from LLMs. Proceedings of the Alexa Prize SocialBot Grand Challenge 5 Proceedings, Available online: https:\/\/www.amazon.science\/alexa-prize\/proceedings\/chirpy-cardinal-dialogue-distillery-crafting-interpolable-interpretable-and-introspectable-dialogue-from-llms."},{"key":"ref_24","unstructured":"Taori, R., Gulrajani, I., Zhang, T., Dubois, Y., Li, X., Guestrin, C., Liang, P., and Hashimoto, T.B. (2023, March 13). Stanford Alpaca: An Instruction-following LLaMA Model. Available online: https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"ref_25","unstructured":"Chung, H.W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., and Brahma, S. (2022). Scaling Instruction-Finetuned Language Models. arXiv."},{"key":"ref_26","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., and Liu, P.J. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv."},{"key":"ref_27","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., and Gehrmann, S. (2022). PaLM: Scaling Language Modeling with Pathways. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Rashkin, H., Smith, E.M., Li, M., and Boureau, Y.L. (2019, January 28). Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset. Proceedings of the ACL, Florence, Italy.","DOI":"10.18653\/v1\/P19-1534"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Radlinski, F., Balog, K., Byrne, B., and Krishnamoorthi, K. (2019, January 11\u201313). Coached Conversational Preference Elicitation: A Case Study in Understanding Movie Preferences. Proceedings of the Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Stockholm, Sweden.","DOI":"10.18653\/v1\/W19-5941"},{"key":"ref_30","unstructured":"Henderson, M., Budzianowski, P., Casanueva, I., Coope, S., Gerz, D., Kumar, G., Mrk\u0161i\u0107, N., Spithourakis, G., Su, P.H., and Vulic, I. (, January July). A Repository of Conversational Datasets. Proceedings of the Workshop on NLP for Conversational AI, Available online: https:\/\/www.github.com\/PolyAI-LDN\/conversational-datasets."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., and Bowman, S.R. (2019). GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. arXiv.","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Jiao, X., Yin, Y., Shang, L., Jiang, X., Chen, X., Li, L., Wang, F., and Liu, Q. (2020). TinyBERT: Distilling BERT for Natural Language Understanding. arXiv.","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref_33","unstructured":"Clark, K., Luong, M.T., Le, Q.V., and Manning, C.D. (2020). ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Atkins, C., Zhao, B.Z.H., Asghar, H.J., Wood, I., and Kaafar, M.A. (2023). Those Aren\u2019t Your Memories, They\u2019re Somebody Else\u2019s: Seeding Misinformation in Chat Bot Memories. arXiv.","DOI":"10.1007\/978-3-031-33488-7_11"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/15\/12\/384\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:32:24Z","timestamp":1760131944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/15\/12\/384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,28]]},"references-count":34,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["fi15120384"],"URL":"https:\/\/doi.org\/10.3390\/fi15120384","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,28]]}}}