PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator
- URL: http://arxiv.org/abs/2308.11534v5
- Date: Mon, 27 May 2024 16:32:16 GMT
- Title: PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator
- Authors: Chuyi Kong, Yaxin Fan, Xiang Wan, Feng Jiang, Benyou Wang,
- Abstract summary: We propose a paradigm to simulate human behavior better and explore the benefits of incorporating more human-like questions in multi-turn conversations.
Specifically, we target human questions extracted from genuine human-machine conversations as a learning goal and provide a novel user simulator called Socratic'
Our results show our response model, PlatoLM', achieves SoTA performance among LLaMA-based 7B models in MT-Bench.
- Score: 39.40718009289621
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The unparalleled performance of closed-sourced ChatGPT has sparked efforts towards its democratization, with notable strides made by leveraging real user and ChatGPT dialogues, as evidenced by Vicuna. However, due to challenges in gathering dialogues involving human participation, current endeavors like Baize and UltraChat rely on ChatGPT conducting roleplay to simulate humans based on instructions, resulting in overdependence on seeds, diminished human-likeness, limited topic diversity, and an absence of genuine multi-round conversational dynamics. To address the above issues, we propose a paradigm to simulate human behavior better and explore the benefits of incorporating more human-like questions in multi-turn conversations. Specifically, we directly target human questions extracted from genuine human-machine conversations as a learning goal and provide a novel user simulator called `Socratic'. The experimental results show our response model, `PlatoLM', achieves SoTA performance among LLaMA-based 7B models in MT-Bench. Our findings further demonstrate that our method introduces highly human-like questioning patterns and rich topic structures, which can teach the response model better than previous works in multi-round conversations.
Related papers
- LLM Roleplay: Simulating Human-Chatbot Interaction [52.03241266241294]
LLM-Roleplay is a goal-oriented, persona-based method to automatically generate diverse multi-turn dialogues simulating human-chatbot interaction.
We collect natural human-chatbot dialogues from different sociodemographic groups and conduct a human evaluation to compare real human-chatbot dialogues with our generated dialogues.
arXiv Detail & Related papers (2024-07-04T14:49:46Z) - Designing and Evaluating Multi-Chatbot Interface for Human-AI Communication: Preliminary Findings from a Persuasion Task [1.360607903399872]
This study examines the impact of multi-chatbot communication in a specific persuasion setting: promoting charitable donations.
We developed an online environment that enables multi-chatbot communication and conducted a pilot experiment.
We present our development process of the multi-chatbot interface and present preliminary findings from a pilot experiment.
arXiv Detail & Related papers (2024-06-28T04:33:41Z) - ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalness [4.564433526993029]
We study how ChatGPT behaves during conversations in different settings by analyzing its interactions in both a normal way and a role-play setting.
Our study highlights the diversity of user motives when interacting with ChatGPT and variable AI naturalness, showing not only the nuanced dynamics of natural conversations between humans and AI, but also providing new avenues for improving the effectiveness of human-AI communication.
arXiv Detail & Related papers (2024-03-26T22:01:13Z) - BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues [72.65163468440434]
This report provides a preliminary evaluation of existing large language models for human-style multi-turn chatting.
We prompt large language models (LLMs) to generate a full multi-turn dialogue based on the ChatSEED, utterance by utterance.
We find GPT-4 can generate human-style multi-turn dialogues with impressive quality, significantly outperforms its counterparts.
arXiv Detail & Related papers (2023-10-20T16:53:51Z) - SMILE: Single-turn to Multi-turn Inclusive Language Expansion via
ChatGPT for Mental Health Support [28.370263099251638]
We introduce SMILE, a single-turn to multi-turn inclusive language expansion technique that prompts ChatGPT to rewrite public single-turn dialogues into multi-turn ones.
We generate a large-scale, diverse, and high-quality dialogue dataset named SmileChat comprising 55,165 dialogues in total with an average of 10.4 turns per dialogue.
To better assess the overall quality of SmileChat, we collect a real-life chat dataset comprising 82 counseling dialogues for model evaluation.
arXiv Detail & Related papers (2023-04-30T11:26:10Z) - TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real
World [97.58623810402563]
We introduce a new video-based multi-modal dialogue dataset, called TikTalk.
We collect 38K videos from a popular video-sharing platform, along with 367K conversations posted by users beneath them.
Users engage in spontaneous conversations based on their multi-modal experiences from watching videos, which helps recreate real-world chitchat context.
arXiv Detail & Related papers (2023-01-14T10:18:22Z) - Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion [89.01668641930206]
We present a framework for modeling interactional communication in dyadic conversations.
We autoregressively output multiple possibilities of corresponding listener motion.
Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions.
arXiv Detail & Related papers (2022-04-18T17:58:04Z) - Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn
Chatbot Responding with Intention [55.77218465471519]
This paper proposes an innovative framework to train chatbots to possess human-like intentions.
Our framework included a guiding robot and an interlocutor model that plays the role of humans.
We examined our framework using three experimental setups and evaluate the guiding robot with four different metrics to demonstrated flexibility and performance advantages.
arXiv Detail & Related papers (2021-03-30T15:24:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.