We present a novel end-to-end personality-based synthetic dialogue data generation pipeline, specifically designed to elicit responses from large language models via prompting. We design the prompts to generate more human-like dialogues considering real-world scenarios when users engage with chatbots. We introduce PSYDIAL, the first Korean dialogue dataset focused on personality-based dialogues, curated using our proposed pipeline. Notably, we focus on the Extraversion dimension of the Big Five personality model in our research. Experimental results indicate that while pre-trained models and those fine-tuned with a chit-chat dataset struggle to generate responses reflecting personality, models trained with PSYDIAL show significant improvements. The versatility of our pipeline extends beyond dialogue tasks, offering potential for other non-dialogue related applications. This research opens doors for more nuanced, personality-driven conversational AI in Korean and potentially other languages.

Unsupervised out-of-domain (OOD) detection is a task aimed at discriminating whether given samples are from the in-domain or not, without the categorical labels of in-domain instances. Unlike supervised OOD, as there are no labels for training a classifier, previous works on unsupervised OOD detection adopted the one-class classification (OCC) approach, assuming that the training samples come from a single domain. However, in-domain instances in many real world applications can have a heterogeneous distribution (i.e., across multiple domains or multiple classes). In this case, OCC methods have difficulty in reflecting the categorical information of the domain properly. To tackle this issue, we propose a two-stage framework that leverages the latent categorical information to improve representation learning for textual OOD detection. In the first stage, we train a transformer-based sentence encoder for pseudo labeling by contrastive loss and cluster loss. The second stage is pseudo label learning in which the model is re-trained with pseudo-labels obtained in the first stage. The empirical results on the three datasets show that our two-stage framework significantly outperforms baseline models in more challenging scenarios.

Unsupervised text style transfer is a challenging task that aims to alter the stylistic attributes of a given text without affecting its original content. One of the methods to achieve this is controllable style transfer, which allows for the control of the degree of style transfer. However, an issue encountered with controllable style transfer is the instability of transferred text fluency when the degree of the style transfer changes. To address this problem, we propose a novel approach that incorporates additional syntax parsing information during style transfer. By leveraging the syntactic information, our model is guided to generate natural sentences that effectively reflect the desired style while maintaining fluency. Experimental results show that our method achieves robust performance and improved fluency compared to previous controllable style transfer methods.

In a hate speech detection model, we should consider two critical aspects in addition to detection performance–bias and explainability. Hate speech cannot be identified based solely on the presence of specific words; the model should be able to reason like humans and be explainable. To improve the performance concerning the two aspects, we propose Masked Rationale Prediction (MRP) as an intermediate task. MRP is a task to predict the masked human rationales–snippets of a sentence that are grounds for human judgment–by referring to surrounding tokens combined with their unmasked rationales. As the model learns its reasoning ability based on rationales by MRP, it performs hate speech detection robustly in terms of bias and explainability. The proposed method generally achieves state-of-the-art performance in various metrics, demonstrating its effectiveness for hate speech detection. Warning: This paper contains samples that may be upsetting.

The prevalent approach for unsupervised text style transfer is disentanglement between content and style. However, it is difficult to completely separate style information from the content. Other approaches allow the latent text representation to contain style and the target style to affect the generated output more than the latent representation does. In both approaches, however, it is impossible to adjust the strength of the style in the generated output. Moreover, those previous approaches typically perform both the sentence reconstruction and style control tasks in a single model, which complicates the overall architecture. In this paper, we address these issues by separating the model into a sentence reconstruction module and a style module. We use the Transformer-based autoencoder model for sentence reconstruction and the adaptive style embedding is learned directly in the style module. Because of this separation, each module can better focus on its own task. Moreover, we can vary the style strength of the generated sentence by changing the style of the embedding expression. Therefore, our approach not only controls the strength of the style, but also simplifies the model architecture. Experimental results show that our approach achieves better style transfer performance and content preservation than previous approaches.