arXiv Computer Science @arxiv_cs@qoto.org

Reducing energy consumption is essential to lessen greenhouse gas emissions, conserve natural resources, and help mitigate the impacts of climate change. In this direction, edge computing, a complementary technology to cloud computing, extends computational capabilities closer to the data producers, enabling energy-efficient and latency-sensitive service delivery for end users. To properly manage data and microservice storage, expanding the Docker Hub registry to the edge using an AWS S3-compatible MinIO-based object storage service can reduce completion time and energy consumption. To address this, we introduce Docker rEgistry-based Edge dataflow Processing (DEEP) to optimize the energy consumption of microservice-based application deployments by focusing on deployments from Docker Hub and MinIO-based regional registries and their processing on edge devices. After applying nash equilibrium and benchmarking the execution of two compute-intensive machine learning (ML) applications of video and text processing, we compare energy consumption across three deployment scenarios: exclusively from Docker Hub, exclusively from the regional registry, and a hybrid method utilizing both. Experimental results show that deploying 83% of text processing microservices from the regional registry improves the energy consumption by 0.34% (18J) compared to microservice deployments exclusively from Docker Hub.

An increasing reliance on recommender systems has led to concerns about the creation of filter bubbles on social media, especially on short video platforms like TikTok. However, their formation is still not entirely understood due to the complex dynamics between recommendation algorithms and user feedback. In this paper, we aim to shed light on these dynamics using a large language model-based simulation framework. Our work employs real-world short-video data containing rich video content information and detailed user-agents to realistically simulate the recommendation-feedback cycle. Through large-scale simulations, we demonstrate that LLMs can replicate real-world user-recommender interactions, uncovering key mechanisms driving filter bubble formation. We identify critical factors, such as demographic features and category attraction that exacerbate content homogenization. To mitigate this, we design and test interventions including various cold-start and feedback weighting strategies, showing measurable reductions in filter bubble effects. Our framework enables rapid prototyping of recommendation strategies, offering actionable solutions to enhance content diversity in real-world systems. Furthermore, we analyze how LLM-inherent biases may propagate through recommendations, proposing safeguards to promote equity for vulnerable groups, such as women and low-income populations. By examining the interplay between recommendation and LLM agents, this work advances a deeper understanding of algorithmic bias and provides practical tools to promote inclusive digital spaces.

With the rapid advancement of large language models, academic topic identification and topic evolution analysis are crucial for enhancing AI's understanding capabilities. Dynamic topic analysis provides a powerful approach to capturing and understanding the temporal evolution of topics in large-scale datasets. This paper presents a two-stage dynamic topic analysis framework that incorporates convex optimization to improve topic consistency, sparsity, and interpretability. In Stage 1, a two-layer non-negative matrix factorization (NMF) model is employed to extract annual topics and identify key terms. In Stage 2, a convex optimization algorithm refines the dynamic topic structure using the convex NMF (cNMF) model, further enhancing topic integration and stability. Applying the proposed method to IEEE journal abstracts from 2004 to 2022 effectively identifies and quantifies emerging research topics, such as COVID-19 and digital twins. By optimizing sparsity differences in the clustering feature space between traditional and emerging research topics, the framework provides deeper insights into topic evolution and ranking analysis. Moreover, the NMF-cNMF model demonstrates superior stability in topic consistency. At sparsity levels of 0.4, 0.6, and 0.9, the proposed approach improves topic ranking stability by 24.51%, 56.60%, and 36.93%, respectively. The source code (to be open after publication) is available at https://github.com/meetyangyang/CDNMF.

ExpertRAG is a novel theoretical framework that integrates Mixture-of-Experts (MoE) architectures with Retrieval Augmented Generation (RAG) to advance the efficiency and accuracy of knowledge-intensive language modeling. We propose a dynamic retrieval gating mechanism coupled with expert routing, enabling the model to selectively consult an external knowledge store or rely on specialized internal experts based on the query's needs. The paper lays out the theoretical foundations of ExpertRAG, including a probabilistic formulation that treats retrieval and expert selection as latent decisions, and mathematical justifications for its efficiency in both computation and knowledge utilization. We derive formulae to quantify the expected computational cost savings from selective retrieval and the capacity gains from sparse expert utilization. A comparative analysis positions ExpertRAG against standard RAG (with always-on retrieval) and pure MoE models (e.g., Switch Transformer, Mixtral) to highlight its unique balance between parametric knowledge and non-parametric retrieval. We also outline an experimental validation strategy, proposing benchmarks and evaluation protocols to test ExpertRAG's performance on factual recall, generalization, and inference efficiency. The proposed framework, although presented theoretically, is supported by insights from prior work in RAG and MoE, and is poised to provide more factual, efficient, and adaptive generation by leveraging the best of both paradigms. In summary, ExpertRAG contributes a new perspective on scaling and augmenting language models, backed by a thorough analysis and a roadmap for empirical validation.

Personalization with retrieval-augmented generation (RAG) often fails to capture fine-grained features of authors, making it hard to identify their unique traits. To enrich the RAG context, we propose providing Large Language Models (LLMs) with author-specific features, such as average sentiment polarity and frequently used words, in addition to past samples from the author's profile. We introduce a new feature called Contrastive Examples: documents from other authors are retrieved to help LLM identify what makes an author's style unique in comparison to others. Our experiments show that adding a couple of sentences about the named entities, dependency patterns, and words a person uses frequently significantly improves personalized text generation. Combining features with contrastive examples boosts the performance further, achieving a relative 15% improvement over baseline RAG while outperforming the benchmarks. Our results show the value of fine-grained features for better personalization, while opening a new research dimension for including contrastive examples as a complement with RAG. We release our code publicly.

Recent advancements in language models and pre-trained language models like BERT and RoBERTa have revolutionized natural language processing, enabling a deeper understanding of human-like language. In this paper, we explore enhancing recommender systems using textual embeddings from pre-trained language models to address the limitations of traditional recommender systems that rely solely on explicit features from users, items, and user-item interactions. By transforming structured data into natural language representations, we generate high-dimensional embeddings that capture deeper semantic relationships between users, items, and contexts. Our experiments demonstrate that this approach significantly improves recommendation accuracy and relevance, resulting in more personalized and context-aware recommendations. The findings underscore the potential of PLMs to enhance the effectiveness of recommender systems.

This paper focuses on a typical uplink transmission scenario over multiple-input multiple-output multiple access channel (MIMO-MAC) and thus propose a multi-user learnable CSI fusion semantic communication (MU-LCFSC) framework. It incorporates CSI as the side information into both the semantic encoders and decoders to generate a proper feature mask map in order to produce a more robust attention weight distribution. Especially for the decoding end, a cooperative successive interference cancellation procedure is conducted along with a cooperative mask ratio generator, which flexibly controls the mask elements of feature mask maps. Numerical results verify the superiority of proposed MU-LCFSC compared to DeepJSCC-NOMA over 3 dB in terms of PSNR.

In the era of Large Language Models (LLMs), establishing effective evaluation methods and standards for diverse human-AI interaction systems is increasingly challenging. To encourage more transparent documentation and facilitate discussion on human-AI system evaluation design options, we present an evaluation card SPHERE, which encompasses five key dimensions: 1) What is being evaluated?; 2) How is the evaluation conducted?; 3) Who is participating in the evaluation?; 4) When is evaluation conducted?; 5) How is evaluation validated? We conduct a review of 39 human-AI systems using SPHERE, outlining current evaluation practices and areas for improvement. We provide three recommendations for improving the validity and rigor of evaluation practices.

Recent advancements in Multi-modal Large Language Models (MLLMs) have led to significant progress in developing GUI agents for general tasks such as web browsing and mobile phone use. However, their application in professional domains remains under-explored. These specialized workflows introduce unique challenges for GUI perception models, including high-resolution displays, smaller target sizes, and complex environments. In this paper, we introduce ScreenSpot-Pro, a new benchmark designed to rigorously evaluate the grounding capabilities of MLLMs in high-resolution professional settings. The benchmark comprises authentic high-resolution images from a variety of professional domains with expert annotations. It spans 23 applications across five industries and three operating systems. Existing GUI grounding models perform poorly on this dataset, with the best model achieving only 18.9%. Our experiments reveal that strategically reducing the search area enhances accuracy. Based on this insight, we propose ScreenSeekeR, a visual search method that utilizes the GUI knowledge of a strong planner to guide a cascaded search, achieving state-of-the-art performance with 48.1% without any additional training. We hope that our benchmark and findings will advance the development of GUI agents for professional applications. Code, data and leaderboard can be found at https://gui-agent.github.io/grounding-leaderboard.

Large Language Models (LLMs) have made significant strides in Natural Language Processing but remain vulnerable to fairness-related issues, often reflecting biases inherent in their training data. These biases pose risks, particularly when LLMs are deployed in sensitive areas such as healthcare, finance, and law. This paper introduces a metamorphic testing approach to systematically identify fairness bugs in LLMs. We define and apply a set of fairness-oriented metamorphic relations (MRs) to assess the LLaMA and GPT model, a state-of-the-art LLM, across diverse demographic inputs. Our methodology includes generating source and follow-up test cases for each MR and analyzing model responses for fairness violations. The results demonstrate the effectiveness of MT in exposing bias patterns, especially in relation to tone and sentiment, and highlight specific intersections of sensitive attributes that frequently reveal fairness faults. This research improves fairness testing in LLMs, providing a structured approach to detect and mitigate biases and improve model robustness in fairness-sensitive applications.

As the prevalence of mental health crises increases on social media platforms, identifying and preventing potential harm has become an urgent challenge. This study introduces a large language model (LLM)-based text transfer recognition method for social network crisis intervention, enhanced with domain-specific mental health knowledge. We propose a multi-level framework that incorporates transfer learning using BERT, and integrates mental health knowledge, sentiment analysis, and behavior prediction techniques. The framework includes a crisis annotation tool trained on social media datasets from real-world events, enabling the model to detect nuanced emotional cues and identify psychological crises. Experimental results show that the proposed method outperforms traditional models in crisis detection accuracy and exhibits greater sensitivity to subtle emotional and contextual variations.

Research background: With the continuous development of society, consumers pay more attention to the key information of product fine-grained attributes when shopping. Research purposes: This study will fine tune the Sentence-BERT word embedding model and LDA model, mine the subject characteristics in online reviews of goods, and show consumers the details of various aspects of goods. Research methods: First, the Sentence-BERT model was fine tuned in the field of e-commerce online reviews, and the online review text was converted into a word vector set with richer semantic information; Secondly, the vectorized word set is input into the LDA model for topic feature extraction; Finally, focus on the key functions of the product through keyword analysis under the theme. Results: This study compared this model with other word embedding models and LDA models, and compared it with common topic extraction methods. The theme consistency of this model is 0.5 higher than that of other models, which improves the accuracy of theme extraction

Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial redundancy in the CoT reasoning traces, which not only increases inference latency but also negatively impacts model performance by diverting attention to unnecessary reasoning paths. To address this issue, we investigate the internal reasoning structures of LLMs and categorize them into three primary thought types: execution, reflection, and transition thoughts. Moreover, our analysis reveals that excessive reflection and transition thoughts are strongly correlated with failure cases and these thought categories exhibit clear separation in the latent space. Based on these, we introduce SEAL (Steerable reasoning calibration), a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains. SEAL consists of an offline stage for extracting the reasoning steering vector in the latent space, followed by an on-the-fly calibration of the reasoning trace through representation intervention using the steering vector. Notably, the steering vector exhibits strong transferability across various tasks. Extensive experiments across multiple models (DeepSeek-R1-Distill and QwQ-32B-Preview) and benchmarks (Math500, GSM8K, LiveCodeBench) validate the effectiveness of SEAL, up to a 11% improvement in accuracy while reducing reasoning tokens by 11.8% to 50.4%. Our code is publicly available at https://github.com/VITA-Group/SEAL.

Small Language Models (SLMs) offer efficient alternatives to LLMs for specific domains. The 2023 TinyStories study developed an English dataset that allows SLMs with 1 to 10 million parameters to produce coherent outputs. Our research expands this framework by translating the original dataset into Indian languages and creating synthetic data using LLMs. We focus on Hindi, Marathi, and Bengali, evaluating SLMs for regional language processing and understanding linguistic complexity. We show that SLMs efficiently process regional languages with significantly fewer parameters than LLMs, providing a complementary framework for ``inference based evaluation" of tokenization strategies and linguistic complexity. Our analysis shows that language-specific tokenizers outperform general-purpose ones for Indian languages. Empirical validations, supported by information-theoretic and morphological analyses, provides fundamental understanding behind the better performance of Hindi models over Marathi and Bengali. Additionally, we show that synthetic datasets outperform translated content for training SLMs. Correlation analyses reveal cross-linguistic patterns and language-specific relationships between creativity, grammatical precision, and narrative completeness. These findings advance both the practical application of SLMs to underserved languages and our theoretical understanding of neural language development.

Large language model (LLM)-driven AI systems may exhibit an inference failure mode we term `neural howlround,' a self-reinforcing cognitive loop where certain highly weighted inputs become dominant, leading to entrenched response patterns resistant to correction. This paper explores the mechanisms underlying this phenomenon, which is distinct from model collapse and biased salience weighting. We propose an attenuation-based correction mechanism that dynamically introduces counterbalancing adjustments and can restore adaptive reasoning, even in `locked-in' AI systems. Additionally, we discuss some other related effects arising from improperly managed reinforcement. Finally, we outline potential applications of this mitigation strategy for improving AI robustness in real-world decision-making tasks.

Ontology-based question generation is an important application of semantic-aware systems that enables the creation of large question banks for diverse learning environments. The effectiveness of these systems, both in terms of the calibre and cognitive difficulty of the resulting questions, depends heavily on the quality and modelling approach of the underlying ontologies, making it crucial to assess their fitness for this task. To date, there has been no comprehensive investigation into the specific ontology aspects or characteristics that affect the question generation process. Therefore, this paper proposes a set of requirements and task-specific metrics for evaluating the fitness of ontologies for question generation tasks in pedagogical settings. Using the ROMEO methodology, a structured framework for deriving task-specific metrics, an expert-based approach is employed to assess the performance of various ontologies in Automatic Question Generation (AQG) tasks, which is then evaluated over a set of ontologies. Our results demonstrate that ontology characteristics significantly impact the effectiveness of question generation, with different ontologies exhibiting varying performance levels. This highlights the importance of assessing ontology quality with respect to AQG tasks.

Open science movement has established reproducibility, transparency, and validation of research outputs as essential norms for conducting scientific research. It advocates for open access to research outputs, especially research data, to enable verification of published findings and its optimum reuse. The FAIR (Findable, Accessible, Interoperable, and Reusable) data principles support the philosophy of open science and have emerged as a foundational framework for making digital assets machine-actionable and enhancing their reusability and value in various domains, particularly in scientific research and data management. In response to the growing demand for making data FAIR, various FAIR implementation frameworks have been developed by various organizations to educate and make the scientific community more aware of FAIR and its principles and to make the adoption and implementation of FAIR easier. This paper provides a comprehensive review of the openly available FAIR implementation frameworks based on a parametric evaluation of these frameworks. The current work identifies 13 frameworks and compares them against their coverage of the four foundational principles of FAIR, including an assessment of these frameworks against 36 parameters related to technical specifications, basic features, and FAIR implementation features and FAIR coverage. The study identifies that most of the frameworks only offer a step-by-step guide to FAIR implementation and seem to be adopting the technology-first approach, mostly guiding the deployment of various tools for FAIR implementation. Many frameworks are missing the critical aspects of explaining what, why, and how for the four foundational principles of FAIR, giving less consideration to the social aspects of FAIR. The study concludes that more such frameworks should be developed, considering the people-first approach rather than the technology-first.

Misinformation continues to pose a significant challenge in today's information ecosystem, profoundly shaping public perception and behavior. Among its various manifestations, Out-of-Context (OOC) misinformation is particularly obscure, as it distorts meaning by pairing authentic images with misleading textual narratives. Existing methods for detecting OOC misinformation predominantly rely on coarse-grained similarity metrics between image-text pairs, which often fail to capture subtle inconsistencies or provide meaningful explainability. While multi-modal large language models (MLLMs) demonstrate remarkable capabilities in visual reasoning and explanation generation, they have not yet demonstrated the capacity to address complex, fine-grained, and cross-modal distinctions necessary for robust OOC detection. To overcome these limitations, we introduce EXCLAIM, a retrieval-based framework designed to leverage external knowledge through multi-granularity index of multi-modal events and entities. Our approach integrates multi-granularity contextual analysis with a multi-agent reasoning architecture to systematically evaluate the consistency and integrity of multi-modal news content. Comprehensive experiments validate the effectiveness and resilience of EXCLAIM, demonstrating its ability to detect OOC misinformation with 4.3% higher accuracy compared to state-of-the-art approaches, while offering explainable and actionable insights.

Predicting Click-Through Rates is a crucial function within recommendation and advertising platforms, as the output of CTR prediction determines the order of items shown to users. The Embedding \& MLP paradigm has become a standard approach for industrial recommendation systems and has been widely deployed. However, this paradigm suffers from cold-start problems, where there is either no or only limited user action data available, leading to poorly learned ID embeddings. The cold-start problem hampers the performance of new items. To address this problem, we designed a novel diffusion model to generate a warmed-up embedding for new items. Specifically, we define a novel diffusion process between the ID embedding space and the side information space. In addition, we can derive a sub-sequence from the diffusion steps to expedite training, given that our diffusion model is non-Markovian. Our diffusion model is supervised by both the variational inference and binary cross-entropy objectives, enabling it to generate warmed-up embeddings for items in both the cold-start and warm-up phases. Additionally, we have conducted extensive experiments on three recommendation datasets. The results confirmed the effectiveness of our approach.