Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)

The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In this study, we investigate how varying levels of prompt politeness affect model accuracy on multiple-choice questions. We created a dataset of 50 base questions spanning mathematics, science, and history, each rewritten into five tone variants: Very Polite, Polite, Neutral, Rude, and Very Rude, yielding 250 unique prompts. Using ChatGPT 4o, we evaluated responses across these conditions and applied paired sample t-tests to assess statistical significance. Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that associated rudeness with poorer outcomes, suggesting that newer LLMs may respond differently to tonal variation. Our results highlight the importance of studying pragmatic aspects of prompting and raise broader questions about the social dimensions of human-AI interaction.

Towards a Formal Framework for Partial Compliance of Business Processes

Binary "YES-NO" notions of process compliance are not very helpful to managers for assessing the operational performance of their company because a large number of cases fall in the grey area of partial compliance. Hence, it is necessary to have ways to quantify partial compliance in terms of metrics and be able to classify actual cases by assigning a numeric value of compliance to them. In this paper, we formulate an evaluation framework to quantify the level of compliance of business processes across different levels of abstraction (such as task,trace and process level) and across multiple dimensions of each task (such as temporal, monetary, role-, data-, and quality-related) to provide managers more useful information about their operations and to help them improve their decision making processes. Our approach can also add social value by making social services provided by local, state and federal governments more flexible and improving the lives of citizens.

TraceWalk: Semantic-based Process Graph Embedding for Consistency Checking

Process consistency checking (PCC), an interdiscipline of natural language processing (NLP) and business process management (BPM), aims to quantify the degree of (in)consistencies between graphical and textual descriptions of a process. However, previous studies heavily depend on a great deal of complex expert-defined knowledge such as alignment rules and assessment metrics, thus suffer from the problems of low accuracy and poor adaptability when applied in open-domain scenarios. To address the above issues, this paper makes the first attempt that uses deep learning to perform PCC. Specifically, we proposed TraceWalk, using semantic information of process graphs to learn latent node representations, and integrates it into a convolutional neural network (CNN) based model called TraceNet to predict consistencies. The theoretical proof formally provides the PCC's lower limit and experimental results demonstrate that our approach performs more accurately than state-of-the-art baselines.

Process Extraction from Texts via Multi-Task Architecture

Process extraction, a recently emerged interdiscipline, aims to extract procedural knowledge expressed in texts. Previous process extractors heavily depend on domain-specific linguistic knowledge, thus suffer from the problems of poor quality and lack of adaptability. In this paper, we propose a multi-task architecture based model to perform process extraction. This is the first attempt that brings deep learning in process extraction. Specifically, we divide process extraction into three complete and independent subtasks: sentence classification, sentence semantic recognition and semantic role labeling. All of these subtasks are trained jointly, using a weight-sharing multi-task learning (MTL) framework. Moreover, instead of using fixed-size filters, we use multiscale convolutions to perceive more local contextual features. Finally, we propose a recurrent construction algorithm to create a graphical representation from the extracted procedural knowledge. Experimental results demonstrate that our approach can extract more accurate procedural information than state-of-the-art baselines.