V-VAE: A Variational Auto Encoding Framework Towards Fine-Grained Control over Human-Like Chat
This addresses the need for more dynamic and nuanced persona-based chatbots, though it appears incremental as it builds on existing variational auto-encoding methods.
The paper tackles the problem of generating persona-aligned, human-like chatbot responses by proposing V-VAE, a framework with fine-grained control over latent traits like emotional tone and interaction patterns, and it shows that LLMs using V-VAE outperform baselines on benchmarks such as HumanChatBench and DialogBench.
With the continued proliferation of Large Language Model (LLM) based chatbots, there is a growing demand for generating responses that are not only linguistically fluent but also consistently aligned with persona-specific traits in conversations. However, existing role-play and persona-based chat approaches rely heavily on static role descriptions, coarse-grained signal space, and low-quality synthetic data, which fail to capture dynamic fine-grained details in human-like chat. Human-like chat requires modeling subtle latent traits, such as emotional tone, situational awareness, and evolving personality, which are difficult to predefine and cannot be easily learned from synthetic or distillation-based data. To address these limitations, we propose a Verbal Variational Auto-Encoding (V-VAE) framework, containing a variational auto-encoding module and fine-grained control space which dynamically adapts dialogue behaviour based on fine-grained, interpretable latent variables across talking style, interaction patterns, and personal attributes. We also construct a high-quality dataset, HumanChatData, and benchmark HumanChatBench to address the scarcity of high-quality data in the human-like domain. Experiments show that LLMs based on V-VAE consistently outperform standard baselines on HumanChatBench and DialogBench, which further demonstrates the effectiveness of V-VAE and HumanChatData.