Recently, Few-shot Knowledge Graph Completion (FKGC) has emerged as a significant research area, yet it encounters challenges stemming from the complexity of multi-semantic relationships in few-shot scenarios. To address these challenges, we propose Task-guided Diffusion Prototype network for FKGC (TDP-FKGC), a method that generates high-quality prototype representations via a task-guided diffusion process. Initially, we analyze the semantics of entity pairs, leveraging attention mechanisms to select pertinent reference pairs from the support set for the creation of a preliminary prototype. Subsequently, a task-guided diffusion process is formulated within this prototype space, and a conditional denoising model is employed to produce task-specific prototype representations. Experimental results demonstrate that TDP-FKGC outperforms current state-of-the-art FKGC methods on three widely used datasets. Furthermore, ablation experiments and analysis of different relationship types confirm the effectiveness and multi-semantic handling ability of our proposed model.

This research explores the application of reinforcement learning from artificial intelligence feedback (RLAIF) techniques to enhance healthcare consultation models, with the aim of addressing the challenges associated with preference-aligned data synthesis while reducing the dependence on medical experts. Specifically, we investigate the use of RLAIF in the generation of medical dialogues, focusing on two primary challenges: accurately reflecting doctors’ preferences and the unreliability of existing automated assessment systems. To address these issues, we propose a two-stage approach for synthesizing preference-aligned datasets. In the first stage, we leverage the dialogue continuation capabilities of a large language model to sample diverse, contextually aligned dialogue branches, employing one-shot learning for intervention. The second stage involves modeling doctors’ preferences through both outcome and process feedback. For outcome feedback, a rule-based reward system is utilized, whereas a planning-based reward strategy is employed for process feedback. To validate our approach, we develop the Chinese Standardized Patient Test (CSPT) dataset that emphasizes user guiding, instruction following, and synthesis ability, and construct an objective assessment system based on standardized patient testing. Experimental results demonstrate that our data synthesis approach performs well across five datasets, achieving a 17.6% improvement in diagnostic accuracy with outcome feedback and a 23.3% improvement with process feedback.

Generating meaningful assert statements is one of the key challenges in automated test case generation, which requires understanding the intended functionality of the tested code. Recently, deep learning based models have shown promise in improving the performance of assert statement generation. However, the existing models only rely on the test prefixes along with their corresponding focal methods, yet ignore the developer-written summarization. Based on our observations, the summarization contents usually express the intended program behavior or contain parameters that will appear directly in the assert statement. Such information will help existing models address their current inability to accurately predict assert statements. This paper presents a summarization-guided approach for automatically generating assert statements. To derive generic representations for natural language (i.e., summarization) and programming language (i.e., test prefixes and focal methods), we leverage a pre-trained language model as the reference architecture and fine-tune it on the task of assert statement generation. To the best of our knowledge, the proposed approach makes the first attempt to leverage the summarization of focal methods as the guidance for making the generated assert statements more accurate. We demonstrate the effectiveness of our approach on two real-world datasets compared with state-of-the-art models.

Many applications need to meet diverse requirements of a large-scale distributed user group. That challenges the current requirements engineering techniques. Crowd-based requirements engineering was proposed as an umbrella term for dealing with the requirements development in the context of the large-scale user group. However, there are still many issues. Among others, a key issue is how to merge these requirements to produce the synthesized requirements description when a set of requirements descriptions from different participants are received. Appropriate techniques are needed for supporting the requirements synthesis. Diagrams are widely used in industry to represent requirements. This paper chooses the activity diagrams and proposes a novel approach for the activity diagram synthesis which adopts the genetic algorithm to repeatedly modify a population of individual solutions toward an optimal solution. As a result, it can automatically generate a resulting diagram which combines the commonalities as many as possible while leveraging the variabilities of a set of input diagrams. The approach is featured by: 1) the labelled graph proposed as the representation of the candidate solutions during the iterative evolution; 2) the generalized entropy proposed and defined as the measurement of the solutions; 3) the genetic algorithm designed for sorting out the high-quality solution. Four cases of different scales are used to evaluate the effectiveness of the approach. The experimental results show that not only the approach gets high precision and recall but also the resulting diagram satisfies the properties of minimization and information preservation and can support the requirements traceability.