ABSTRACT Introduction Requirements engineering (RE) faces challenges due to the handling of increasingly complex software systems. These challenges can be addressed using generative artificial intelligence (GenAI). Given that GenAI‐based RE has not been systematically analyzed in detail, this review examines the related research, focusing on trends, methodologies, challenges, and future work directions. Methods A systematic methodology for paper selection, data extraction, and feature analysis is used to comprehensively review 238 articles published from 2019 to 2025 and available from major academic databases. Results Although generative pretrained transformer models dominate current applications (67.3% of studies), the research focus remains unevenly distributed across RE phases, with analysis (30.0%) and elicitation (22.1%) receiving the most attention and management (6.8%) remaining underexplored. Three core challenges—reproducibility (66.8%), hallucinations (63.4%), and interpretability (57.1%)—form a tightly interlinked triad affecting trust and consistency, and strong correlations ( co‐occurrence) indicate that these challenges must be addressed holistically. Industrial adoption remains nascent, with > 90% of studies corresponding to early‐stage development and only 1.3% reaching production‐level integration. Evaluation practices show maturity gaps, limited tool/dataset availability, and fragmented benchmarking approaches. Conclusions Despite the transformative potential of GenAI‐based RE, several barriers hinder its practical adoption. The strong correlations among core challenges demand specialized architectures targeting interdependencies rather than isolated solutions. The limited real‐world deployment reflects systemic bottlenecks in generalizability, data quality, and scalable evaluation methods. Successful adoption requires coordinated development across technical robustness, methodological maturity, and governance integration. A multiphase research roadmap emphasizing evaluation infrastructure strengthening, governance‐aware development, and industrial‐scale standardization is proposed.

Recent studies highlight various machine learning (ML)-based techniques for code clone detection, which can be integrated into developer tools such as static code analysis. With the advancements brought by ML in code understanding, MLbased code clone detectors could accurately identify and classify cloned pairs, especially semantic clones, but often operate as black boxes, providing little insight into the decision-making process. Post hoc explainers, on the other hand, aim to interpret and explain the predictions of these ML models after they are made, offering a way to understand the underlying mechanisms driving the model’s decisions. However, current post hoc techniques require white-box access to the ML model or are computationally expensive, indicating a need for advanced post hoc explainers. In this paper, we propose a novel framework that leverages the in-context learning capabilities of large language models to elucidate the predictions made by the ML-based code clone detectors. We perform a study using ChatGPT-4 to explain the code clone results inferred by GraphCodeBERT. We found that our approach is promising as a post hoc explainer by giving the correct explanations up to 98% and offering good explanations 95% of the time. Yet, the explanations and the code line examples given by the LLM are useful in some cases. We also found that lowering the temperature to zero helps increase the accuracy of the explanation. Lastly, we list the insights that can lead to further improvements in future work. This study paves the way for future studies in utilizing LLMs as a post hoc explainer for various software engineering tasks.

Large Language Models (LLMs) are increasingly utilized in a wide range of natural language processing tasks. Despite their growing adoption, concerns regarding their trustworthiness, i.e., reliability and validity across diverse applications, still remain. This paper introduces a novel visual-based LLM testing tool called PromptOps using the principles of metamorphic testing to assess LLMs beyond traditional accuracy metrics. The tool evaluates LLMs on critical properties such as robustness, fairness, and logical consistency. The tool enables users to design custom test cases via visual programming, define specific prompts, and automatically generate diverse test scenarios. PromptOps fosters greater transparency for model developers by identifying areas for improvement in both performance and fairness. The video demonstration of the PromptOps tool is available at https://youtu.be/M6TbvPIt9kE, and the tool is available at https://github.com/MUICT-SERU/PromptOps.

Knowledge graph embeddings encode knowledge by representing entities and relations through vectors or matrices and have been widely employed in conjunction with deep learning to address a diverse range of problems. The effectiveness of knowledge-driven tasks is intrinsically dependent on the quality of these embeddings. To enhance embedding quality, weight information has been incorporated to develop weight-aware knowledge graph embeddings. However, existing weight-aware knowledge graph embedding models are still evaluated using weight-agnostic tasks, indiscriminately treating all triples while disregarding the global weight distribution of the knowledge graph. To bridge this gap, we introduce weight-aware tasks specifically designed for knowledge graph embeddings, namely weight-aware link prediction and weight-aware triple classification , aiming to provide a more comprehensive evaluation of embedding models on weighted knowledge graphs. To validate the effectiveness of the proposed evaluation protocols, we present a general framework, WaExt , which extends conventional deterministic knowledge graph embedding models into their weight-aware counterparts. Extensive evaluations on four classical knowledge graph embedding models and three weighted knowledge graphs, it’s demonstrated that the superiority of the proposed weight-aware evaluation protocol. Moreover, the WaExt framework WaExt achieves competitive performance, outperforming existing methods. The implementation is publicly available at: https://github.com/Diison/WaExt .

The aim of this study is to formally express awareness for modeling practical agent communication. The notion of awareness has been proposed as a set of propositions for each agent, to which he/she pays attention, and has contributed to avoiding \textit{logical omniscience}. However, when an agent guesses another agent's knowledge states, what matters are not propositions but are accessible possible worlds. Therefore, we introduce a partition of possible worlds connected to awareness, that is an equivalence relation, to denote \textit{indistinguishable} worlds. Our logic is called Awareness Logic with Partition ($\mathcal{ALP}$). In this paper, we first show a running example to illustrate a practical social game. Thereafter, we introduce syntax and Kripke semantics of the logic and prove its completeness. Finally, we outline an idea to incorporate some epistemic actions with dynamic operators that change the state of awareness.

Analogical reasoning is one of the most common methods by which human beings use to understand the world and make decisions. It is a dynamic process that explores an analogy between two states of affairs to claim further properties that might be shared between them. This paper tackles the question of how such arguments can be formulated in an assumption-based argumentation (ABA) framework. For that purpose, we introduce a notion of argument-based similarity measure between two argument's structures and a set of principles that such a measure should satisfy. Then, we propose an intuitive extension into an ABA framework, called ABA≈, to deal with analogical reasoning properly. Finally, we also propose a formalization extended from ABA≈, to deal with the dynamics in analogical argumentation and show how a structure can be handled.

High-quality neural machine translation (NMT) systems rely on the availability of large-scale and reliable parallel data. Since Myanmar language is a low-resource language, the parallel corpus of English-Myanmar language pair is sparse in volume. In this paper, we present a simple yet effective framework to create a parallel corpus from the available comparable corpora. Our proposed system first uses self-training and back-translation approaches together with the denoising-based automatic post-editing (DbAPE) system for augmenting synthetic datasets that are used to expand the size of existing comparable corpora. Then, LaBSE-based sentence embeddings and the proposed scoring function are applied to extract parallel sentences from the expanded comparable corpora. The extracted parallel sentences can be used to supplement parallel corpus when training the low-resource English-Myanmar NMT systems. We investigate the effectiveness of our methods by evaluating the NMT systems trained on the concatenation of parallel data created by our framework and an existing dataset. We show that the proposed framework is capable of creating a reliable parallel corpus, and that the created corpus substantially increases translation quality of MT systems trained on the existing parallel data, as measured by automatic evaluation metrics.

Abstractive summarization focuses on generating concise and fluent text from an original document while maintaining the original intent and containing the new words that do not appear in the original document. Recent studies point out that rewriting extractive summaries help improve the performance with a more concise and comprehensible output summary, which uses a sentence as a textual unit. However, a single document sentence normally cannot supply sufficient information. In this paper, we apply elementary discourse unit (EDU) as textual unit of content selection. In order to utilize EDU for generating a high quality summary, we propose a novel summarization model that first designs an EDU selector to choose salient content. Then, the generator model rewrites the selected EDUs as the final summary. To determine the relevancy of each EDU on the entire document, we choose to apply group tag embedding, which can establish the connection between summary sentences and relevant EDUs, so that our generator does not only focus on selected EDUs, but also ingest the entire original document. Extensive experiments on the CNN/Daily Mail dataset have demonstrated the effectiveness of our model.

Existing word embeddings are trained based on word co-occurrence information, which shows to capture well the semantic information of words. However, only using word co-occurrence information is not enough for training word embeddings, the huge knowledge graph resources cannot be ignored for improving the performance of these word embeddings. This paper proposes a novel knowledge-guided word embedding fine-tuning model called KGWE, which aims to utilize the entity embedding from the knowledge graphs to guide the fine-tuning process of word embeddings. The main idea of KGWE is to use entity embeddings as the targets for fine-tuning the representations of words appeared in the entity description of a knowledge graph. We conduct experiments with two famous static word embeddings and five knowledge graph embedding models and evaluate the model with 14 word similarity benchmarks. Our results show that word embeddings fine-tuned through KGWE can outperform the baselined word embeddings.