Sentence-level explanations can miss the bigger picture of how a black-box model behaves across data, which matters most for complex criteria like safety that cannot be defined by a single rule. We trace Logit-Trajectory, which tracks adjacent-layer logit updates as vectors and aggregates them into a reproducible dataset-level trajectory pattern, enabling depth-wise explainability through signals such as coherence and angular rotation. Across 6 languages and 5 NLP tasks, we show these trajectory summaries reveal consistent depth-wise patterns that divergence- and similarity-based baselines often wash out due to scalarization. As a case study where dataset-level intermediate decision structure matters, we evaluate safety classification, reporting both trajectory-level visual separability and classification performance.

In this research, we introduce the Courtroom-LLM framework, a novel multi-LLM structure inspired by legal courtroom processes, aiming to enhance decision-making in ambiguous text classification scenarios. Our approach simulates a courtroom setting within LLMs, assigning roles similar to those of prosecutors, defense attorneys, and judges, to facilitate comprehensive analysis of complex textual cases. We demonstrate that this structured multi-LLM setup can significantly improve decision-making accuracy, particularly in ambiguous situations, by harnessing the synergistic effects of diverse LLM arguments. Our evaluations across various text classification tasks show that the Courtroom-LLM framework outperforms both traditional single-LLM classifiers and simpler multi-LLM setups. These results highlight the advantages of our legal-inspired model in improving decision-making for text classification.

Many statistical facts are conveyed through charts.While various methods have emerged for chart understanding, chart generation typically requires users to manually input code, intent, and other parameters to obtain the desired format on chart generation tools.Recently, the advent of image-generating Large Language Models has facilitated chart generation; however, even this process often requires users to provide numerous constraints for accurate results.In this paper, we propose a loop-based framework for automatically evolving charts in a multi-agent environment.Within this framework, three distinct agents-Chart Code Generator, Chart Replier, and Chart Quality Evaluator-collaborate for iterative, user-tailored chart generation using large language models.Our approach demonstrates an improvement of up to 29.97% in performance compared to first generation, while also reducing generation time by up to 86.9% compared to manual promptbased methods, showcasing the effectiveness of this multi-agent collaboration in enhancing the quality and efficiency of chart generation.

Summarization is one of the important tasks of natural language processing used to distill information. Recently, the sequence-to-sequence method was applied, in a general manner, to summarization tasks. The problem is that a large amount of information must be pre-trained for a specific domain, and information other than input statements cannot be utilized. To compensate for this shortcoming, controllable summarization has recently been in the spotlight. We introduced three properties into controllable summarization: 1) a new human-machine communication input format, 2) a robust constraint-sensitive summarization method for these formats, and 3) a practical interactive summarization interface available to the user. Experiments on the Wizard-of-Wikipedia dataset show that applying this input format and the constraint-sensitive method enhances summarization performance compared to the typical method. A user study shows that the interactive summarization interface is practical and that participants are evaluating it positively.