Language models have shown strong capabilities across a wide range of tasks in software engineering, such as code generation, yet they suffer from hallucinations. While hallucinations have been studied independently in natural language and code generation, their occurrence in tasks involving code changes which have a structurally complex and context-dependent format of code remains largely unexplored. This paper presents the first comprehensive analysis of hallucinations in two critical tasks involving code change to natural language generation: commit message generation and code review comment generation. We quantify the prevalence of hallucinations in recent language models and explore a range of metric-based approaches to automatically detect them. Our findings reveal that approximately 50\% of generated code reviews and 20\% of generated commit messages contain hallucinations. Whilst commonly used metrics are weak detectors on their own, combining multiple metrics substantially improves performance. Notably, model confidence and feature attribution metrics effectively contribute to hallucination detection, showing promise for inference-time detection.\footnote{All code and data will be released upon acceptance.

In this research, we propose an iterative learning hybrid optimization solver developed to strengthen the performance of metaheuristic algorithms in solving the Capacitated Vehicle Routing Problem (CVRP). The iterative hybrid mechanism integrates the proposed Node-Destroyer Model, a machine learning hybrid model that utilized Graph Neural Networks (GNNs) such identifies and selects customer nodes to guide the Large Neighborhood Search (LNS) operator within the metaheuristic optimization frameworks. This model leverages the structural properties of the problem and solution that can be represented as a graph, to guide strategic selections concerning node removal. The proposed approach reduces operational complexity and scales down the search space involved in the optimization process. The hybrid approach is applied specifically to the CVRP and does not require retraining across problem instances of different sizes. The proposed hybrid mechanism is able to improve the performance of baseline metaheuristic algorithms. Our approach not only enhances the solution quality for standard CVRP benchmarks but also proves scalability on very large-scale instances with up to 30,000 customer nodes. Experimental evaluations on benchmark datasets show that the proposed hybrid mechanism is capable of improving different baseline algorithms, achieving better quality of solutions under similar settings.

Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose $\text{M}^{2}$LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that $\text{M}^{2}$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.

This paper introduces the first prompt-based methods for aspect-based sentiment analysis and sentiment classification in Czech. We employ the sequence-to-sequence models to solve the aspect-based tasks simultaneously and demonstrate the superiority of our prompt-based approach over traditional fine-tuning. In addition, we conduct zero-shot and few-shot learning experiments for sentiment classification and show that prompting yields significantly better results with limited training examples compared to traditional fine-tuning. We also demonstrate that pre-training on data from the target domain can lead to significant improvements in a zero-shot scenario.

Despite the rapid progress of Large Language Models (LLMs), their application in agriculture remains limited due to the lack of domain-specific models, curated datasets, and robust evaluation frameworks. To address these challenges, we propose AgriGPT, a domain-specialized LLM ecosystem for agricultural usage. At its core, we design a multi-agent scalable data engine that systematically compiles credible data sources into Agri-342K, a high-quality, standardized question-answer (QA) dataset. Trained on this dataset, AgriGPT supports a broad range of agricultural stakeholders, from practitioners to policy-makers. To enhance factual grounding, we employ Tri-RAG, a three-channel Retrieval-Augmented Generation framework combining dense retrieval, sparse retrieval, and multi-hop knowledge graph reasoning, thereby improving the LLM's reasoning reliability. For comprehensive evaluation, we introduce AgriBench-13K, a benchmark suite comprising 13 tasks with varying types and complexities. Experiments demonstrate that AgriGPT significantly outperforms general-purpose LLMs on both domain adaptation and reasoning. Beyond the model itself, AgriGPT represents a modular and extensible LLM ecosystem for agriculture, comprising structured data construction, retrieval-enhanced generation, and domain-specific evaluation. This work provides a generalizable framework for developing scientific and industry-specialized LLMs. All models, datasets, and code will be released to empower agricultural communities, especially in underserved regions, and to promote open, impactful research.

This review examines recent advances in Parameter-Efficient Fine-Tuning (PEFT), with a focus on Low-Rank Adaptation (LoRA), to optimize Retrieval-Augmented Generation (RAG) systems like Qwen3, DeepSeek, and Kimi. These systems face challenges in understanding and generating authentic Cantonese colloquial expressions due to limited annotated data and linguistic variability. The review evaluates the integration of LoRA within RAG frameworks, benchmarks PEFT methods for retrieval and generation accuracy, identify domain adaptation strategies under limited data, and compares fine-tuning techniques aimed at improving semantic fidelity under data-scarce conditions. A systematic analysis of recent studies employing diverse LoRA variants, synthetic data generation, user feedback integration, and adaptive parameter allocation was conducted to assess their impact on computational efficiency, retrieval precision, linguistic authenticity, and scalability. Findings reveal that dynamic and ensemble LoRA adaptations significantly reduce trainable parameters without sacrificing retrieval accuracy and generation quality in dialectal contexts. However, limitations remain in fully preserving fine-grained linguistic nuances, especially for low-resource settings like Cantonese. The integration of real-time user feedback and domain-specific data remains underdeveloped, limiting model adaptability and personalization. While selective parameter freezing and nonlinear adaptation methods offer better trade-offs between efficiency and accuracy, their robustness at scale remains an open challenge. This review highlights the promise of PEFT-enhanced RAG systems for domain-specific language tasks and calls for future work targeting dialectal authenticity, dynamic adaptation, and scalable fine-tuning pipelines.

As the social implementation of AI has been steadily progressing, research and development related to AI security has also been increasing. However, existing studies have been limited to organizing related techniques, attacks, defenses, and risks in terms of specific domains or AI elements. Thus, it extremely difficult to understand the relationships among them and how negative impacts on stakeholders are brought about. In this paper, we argue that the knowledge, technologies, and social impacts related to AI security should be holistically organized to help understand relationships among them. To this end, we first develop an AI security map that holistically organizes interrelationships among elements related to AI security as well as negative impacts on information systems and stakeholders. This map consists of the two aspects, namely the information system aspect (ISA) and the external influence aspect (EIA). The elements that AI should fulfill within information systems are classified under the ISA. The EIA includes elements that affect stakeholders as a result of AI being attacked or misused. For each element, corresponding negative impacts are identified. By referring to the AI security map, one can understand the potential negative impacts, along with their causes and countermeasures. Additionally, our map helps clarify how the negative impacts on AI-based systems relate to those on stakeholders. We show some findings newly obtained by referring to our map. We also provide several recommendations and open problems to guide future AI security communities.

Ontology alignment plays a crucial role in integrating diverse data sources across domains. There is a large plethora of systems that tackle the ontology alignment problem, yet challenges persist in producing highly quality correspondences among a set of input ontologies. Human-in-the-loop during the alignment process is essential in applications requiring very accurate mappings. User involvement is, however, expensive when dealing with large ontologies. In this paper, we explore the feasibility of using Large Language Models (LLM) as an alternative to the domain expert. The use of the LLM focuses only on the validation of the subset of correspondences where an ontology alignment system is very uncertain. We have conducted an extensive evaluation over several matching tasks of the Ontology Alignment Evaluation Initiative (OAEI), analysing the performance of several state-of-the-art LLMs using different ontology-driven prompt templates. The LLM results are also compared against simulated Oracles with variable error rates.

--Accurate and adaptive network throughput prediction is essential for latency-sensitive and bandwidth-intensive applications in 5G and emerging 6G networks. However, most existing methods rely on centralized training with uniformly collected data, limiting their applicability in heterogeneous mobile environments with non-IID data distributions. This paper presents the first comprehensive benchmarking of federated learning (FL) strategies for throughput prediction in realistic 5G edge scenarios. We evaluate three aggregation algorithms - F edAvg, F edProx, and F edBN-across four time-series architectures: LSTM, CNN, CNN+LSTM, and Transformer, using five diverse real-world datasets. We systematically analyze the effects of client heterogeneity, cohort size, and history window length on prediction performance. Our results reveal key trade-offs among model complexities, convergence rates, and generalization. It is found that F edBN consistently delivers robust performance under non-IID conditions. LSTM is, therefore, found to achieve a favorable balance between accuracy, rounds, and temporal footprint. T o validate the end-to-end applicability of the framework, we have integrated our FL-based predictors into a live adaptive streaming pipeline. It is seen that F edBN-based LSTM and Transformer models improve mean QoE scores by 11.7% and 11.4%, respectively, over F edAvg, while also reducing the variance. These findings offer actionable insights for building scalable, privacy-preserving, and edge-aware throughput prediction systems in next-generation wireless networks. HE increasing demand for high-bandwidth, low-latency applications in next-generation wireless networks, such as 5G and the emerging 6G, has made accurate and robust network throughput prediction indispensable for sustaining performance under dynamic and resource-constrained network conditions. Dutta and B.Palit are with the Department of Electronics and Communication Engineering, National Institute of Technology Rourkela, India - 769008.

Structure elucidation is a fundamental technique for understanding the microscopic composition of matter and is widely applied across various disciplines in the natural sciences and engineering. However, existing methods often rely heavily on prior databases or known structural information, making it difficult to resolve unknown structures. In addition, complex structures typically require the joint analysis of multiple spectroscopic modalities. This process heavily depends on expert domain knowledge and is often accompanied by high costs in terms of both time and instrumentation. To address these challenges, we propose SpectraLLM, the first large language model designed to support multi-modal spectroscopic joint reasoning. SpectraLLM is capable of processing either single or multiple spectroscopic inputs and performing end-to-end structure elucidation. By integrating continuous and discrete spectroscopic modalities into a shared semantic space, SpectraLLM learns to uncover substructural patterns that are consistent and complementary across spectra, enabling precise molecular structure elucidation. We pretrain and fine-tune SpectraLLM in the domain of small molecules, and evaluate it on six standardized, publicly available chemical datasets. The model achieves state-of-the-art performance, significantly outperforming existing approaches trained on single modalities. Notably, SpectraLLM demonstrates strong robustness and generalization even for single-spectrum inference, while its multi-modal reasoning capability further improves the accuracy of structural prediction.