We present Spoiler Court, a multi-agent adversarial framework for interpretable spoiler detection in movie reviews. Three LLM agents, acting as the Plaintiff, Defendant, and Judge, engage in a multi-round courtroom debate to identify spoiler spans, challenge them, and deliver a final judgement with an interpretable audit trail grounded in the movie’s plot summary. Unlike prior work that produces only binary labels, Spoiler Court outputs which sentences are spoilers, why (via plot fact citations), and how the decision was reached (via adversarial debate transcripts). To evaluate the effectiveness of our approach, we construct a multi-genre evaluation dataset spanning 4 movies with binary and character-level span annotations. Under controlled conditions, Spoiler Court achieves an average F1 of 0.733 across 4 movies, outperforming other baselines including a dedicated spoiler detection framework.

Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent conversations, failing to capture the complexities of real-world multi-user interactions. In this study, we assess the robustness of LLMs in multi-user DST while minimizing dataset construction costs. Inspired by recent advances in LLM-based data annotation, we extend an existing DST dataset by generating utterances of a second user based on speech act theory. Our methodology systematically incorporates a second user’s utterances into conversations, enabling a controlled evaluation of LLMs in multi-user settings. Experimental results reveal a significant performance drop compared to single-user DST, highlighting the limitations of current LLMs in extracting and tracking dialogue states amidst multiple speakers. Our findings emphasize the need for future research to enhance LLMs for multi-user DST scenarios, paving the way for more realistic and robust DST models.

Efforts to leverage deep learning models in low-resource regimes have led to numerous augmentation studies. However, the direct application of methods, such as mixup and cutout, is limited due to the discrete characteristics of the textual data. While methods using pre trained language models have exhibited good efficiency, they require additional considerations for robustness. Inspired by recent studies on decision boundaries, this paper proposes a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models. The proposed technique first focuses on shifting the latent features closer to the decision boundary, followed by reconstruction to generate an ambiguous version with a soft label. Additionally, mid-K sampling is suggested to enhance the diversity of the generated sentences. This paper demonstrates the performance of the proposed augmentation strategy compared to other methods through extensive experiments. Furthermore, the ablation study demonstrates the effect of soft labels and mid-K sampling and the extensibility of the method with curriculum data augmentation.

Text data augmentation is a complex problem due to the discrete nature of sentences. Although rule-based augmentation methods are widely adopted in real-world applications because of their simplicity, they suffer from potential semantic damage. Previous researchers have suggested easy data augmentation with soft labels (softEDA), employing label smoothing to mitigate this problem. However, finding the best factor for each model and dataset is challenging; therefore, using softEDA in real-world applications is still difficult. In this paper, we propose adapting AutoAugment to solve this problem. The experimental results suggest that the proposed method can boost existing augmentation methods and that rule-based methods can enhance cutting-edge pretrained language models. We offer the source code.