Abstract
Conversational agents (CA) are engaged in interactive conversations with users, providing responses and assistance while combining Natural Language Processing (NLP), Understanding (NLU), and Generating (NLG) techniques. Two tiers of conversational agent derivation from Large Language Models (LLMs) exist. The first tier involves conversational fine-tuning from datasets, representing expected user questions and desired conversational agent responses. The second tier requires manual prompting by human operators and evaluation of model output, which is then used for further fine-tuning. Fine-tuning with Reinforcement Learning from Human Feedback (RLHF) models perform better but are resource-intensive and specific for each model. Another critical difference in the performance of various CA is their ability to access auxiliary services for task delegation.
Chapter PDF
References
Joseph Weizenbaum. Eliza—a computer program for the study of natural language communication between man and machine. Commun. ACM, 9(1):36–45, jan 1966.
Mohammad Amin Kuhail, Nazik Alturki, Salwa Alramlawi, and Kholood Alhejori. Interacting with educational chatbots: A systematic review. Education and Information Technologies, 28(1):973–1018, 2023.
Long Ouyang et al. Training language models to follow instructions with human feedback. CoRR, abs/2203.02155, 2022.
Yusuf Mehdi. Reinventing search with a new ai-powered microsoft bing and edge, your copilot for the web, February 2023.
OpenAI. Gpt-4 technical report. CoRR, abs/2303.08774, 2023.
Yusuf Mehdi. Confirmed: the new bing runs on openai’s gpt-4, March 2023.
LinusTechTips. Our biggest sponsor pulled out - wan show february 10, 2023, Feb. 2023.
Kurt Shuster et al. Language models that seek for knowledge: Modular search & generation for dialogue and prompt completion. CoRR, abs/2203.13224, 2022.
Amelia Glaese et al. Improving alignment of dialogue agents via targeted human judgements. CoRR, abs/2209.14375, 2022.
James Vincent. Microsoft’s bing is an emotionally manipulative liar, and people love it. The Verge, February 2023.
Yuntao Bai et al. Constitutional AI: harmlessness from AI feedback. CoRR, abs/2212.08073, 2022.
Nazneen Rajani, Nathan Lambert, Victor Sanh, and Thomas Wolf. What makes a dialog agent useful? Hugging Face Blog, 2023. https://huggingface.co/blog/dialog-agents.
Lianmin Zheng et al. Judging llm-as-a-judge with mt-bench and chatbot arena, 2023.
Hugo Touvron et al. Llama: Open and efficient foundation language models. CoRR, abs/2302.13971, 2023.
Hugo Touvron et al. Llama 2: Open foundation and fine-tuned chat models, 2023.
Yuntao Bai et al. Training a helpful and harmless assistant with reinforcement learning from human feedback. CoRR, abs/2204.05862, 2022.
Together. Announcing openchatkit, March 2023.
Niklas Muennighoff et al. Crosslingual generalization through multitask finetuning, 2022.
Hyung Won Chung et al. Scaling instruction-finetuned language models. CoRR, abs/2210.11416, 2022.
Romal Thoppilan et al. Lamda: Language models for dialog applications. CoRR, abs/2201.08239, 2022.
M Emily Bender. Human-like programs abuse our empathy – even google engineers aren’t immune. The Guardian, 2022.
Kurt Shuster et al. Blenderbot 3: a deployed conversational agent that continually learns to responsibly engage. CoRR, abs/2208.03188, 2022.
Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. BLIP-2: bootstrap** language-image pre-training with frozen image encoders and large language models. CoRR, abs/2301.12597, 2023.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Copyright information
© 2024 The Author(s)
About this chapter
Cite this chapter
Dolamic, L. (2024). Conversational Agents. In: Kucharavy, A., Plancherel, O., Mulder, V., Mermoud, A., Lenders, V. (eds) Large Language Models in Cybersecurity. Springer, Cham. https://doi.org/10.1007/978-3-031-54827-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-54827-7_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54826-0
Online ISBN: 978-3-031-54827-7
eBook Packages: Computer ScienceComputer Science (R0)