Modern data and Machine Learning (ML) pipelines are developed as code repositories but must be manually transformed into deployable artifacts such as Docker images and Kubernetes workflows, a process prone to dependency and configuration errors. While Large Language Models (LLMs) can assist with code understanding, they often fail on multifile repositories due to missing structural context and incomplete dependency resolution. We propose a multi-agent graph-based Retrieval-Augmented Generation (GraphRAG) framework that automates the generation of deployment artifacts from code repositories. The framework constructs an Abstract Syntax Tree (AST)-grounded knowledge graph, performs structure-aware retrieval, and coordinates specialized agents to synthesize containerization and workflow specifications. The system further improves reliability through iterative self-healing driven by execution logs. Evaluated on 17 GitHub repositories spanning ETL, ML training, and LLM-based evaluation pipelines, our approach achieves 65% end-to-end execution success on Kubernetes, outperforming a vector-only RAG baseline (24%) and a single-agent GraphRAG variant (47%). These results indicate that combining graph-centric retrieval with agent decomposition improves execution reliability.

Large Language Models (LLMs) have transformed Recommendation Systems (RecSys) by enabling more user-aware interactions. However, this shift raises new challenges in evaluating fairness, particularly due to confounding systemic biases such as popularity bias. Conventional fairness assessments often confuse disparities in user treatment with systemic biases toward popular items, resulting in misleading conclusions. In this paper, we introduce PureBiasoMeter, a diagnostic framework that decouples popularity bias from user-level fairness in LLM-based RecSys. Our approach is based on the hypothesis that accurate fairness evaluation requires first mitigating popularity bias and then remeasuring fairness metrics. We generate a comprehensive set of 72 prompts using different user profiling strategies, demographic variants, and bias mitigation instructions. By applying these prompts in a black-box LLM setting, we evaluate fairness sensitivity, recommendation quality, and bias levels across multiple dimensions. Our results demonstrate that removing popularity bias substantially alters fairness measurements and reveals underlying disparities that were previously unknown. PureBiasoMeter thus provides a more reliable basis for fairness analysis and contributes a practical tool for disentangling intertwined sources of bias in modern RecSys.

Large Language Models (LLMs) often produce outputs that reflect social biases, toxicity, or unfair treatment of demographic groups, undermining trust and fairness. While prior mitigation strategies frequently rely on complex architectures, access to model internals, or costly fine-tuning, we argue that simplicity can be a strength. We introduce StarDTox, a lightweight, critique-and-revise multi-agent framework that leverages the LLM's own internal knowledge, via a small number of coordinated prompts, to self-correct harmful outputs. Dedicated agents independently assess bias and overall output quality, and their feedback is integrated to guide prompt-based revision. Without modifying model weights or requiring any extra finetuning, StarDTox offers strong bias mitigation and high-quality outputs across both open-ended text generation and structured tasks, outperforming other baselines. For the text generation task, on the RealToxicityPrompt dataset, it reduces toxicity by over 50% compared to other baselines, while maintaining over 90% fluency. In addition, in structured tasks, on the BBQ benchmark, it achieves the lowest bias scores across both ambiguous and disambiguated examples, without sacrificing accuracy.

Reproducibility is a cornerstone of scientific progress, allowing researchers to validate findings and build upon previous work. While reproducibility has been an important issue in traditional recommender systems, the rise of Large Language Model (LLM)-based recommendation systems introduces new challenges, particularly in top-N recommendation tasks. In this study, we investigate the reproducibility of state-of-the-art LLM-based recommendation systems. We categorize key factors affecting the reproducibility of recommendation performance into four groups: code, data, methodological details, and evaluation. Our findings highlight significant performance fluctuations based on these factors, emphasizing the need for these factors to be clearly documented and considered during evaluations. To enhance reproducibility, we propose LLMReClarify, a comprehensive set of guidelines adapted from the NeurIPS reproducibility checklist, tailored specifically for LLM-based recommendation systems.

Relation Extraction (RE) models are crucial to many Natural Language Processing (NLP) applications, but often inherit and deepen biases in their training data. The underrepresentation of certain demographic groups can lead to performance disparities, particularly when considering intersectional fairness, where biases intersect across attributes such as gender and ancestry. To address this issue, we present IntersectionRE, a framework to improve the representation of underrepresented groups by generating synthetic training data. IntersectionRE identifies gaps in demographic coverage and optimizes data generation, ensuring the quality of augmented data through Large Language Models (LLMs), perplexity scoring, and factual consistency validation. Experimental results on the NYT-10, and Wiki-ZSL datasets demonstrate that our approach effectively reduces intersectional representation and model performance disparities, particularly for historically underrepresented groups.

In Machine Learning (ML) and Deep Learning (DL) research, ablation studies are typically performed to provide insights into the individual contribution of different building blocks and components of an ML/DL system (e.g., a deep neural network), as well as to justify that certain additions or modifications to an existing ML/DL system can result in the proposed improved performance. Although dedicated frameworks for performing ablation studies have been introduced in recent years, conducting such experiments is still associated with requiring tedious, redundant work, typically involving maintaining redundant and nearly identical versions of code that correspond to different ablation trials. Inspired by the recent promising performance of Large Language Models (LLMs) in the generation and analysis of ML/DL code, in this paper we discuss the potential of LLMs as facilitators of ablation study experiments for scientific research projects that involve or deal with ML and DL models. We first discuss the different ways in which LLMs can be utilized for ablation studies and then present the prototype of a tool called AblationMage, that leverages LLMs to semi-automate the overall process of conducting ablation study experiments. We showcase the usability of AblationMage as a tool through three experiments, including one in which we reproduce the ablation studies from a recently published applied DL paper.

Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology leveraging speaker assignment as an analytic tool for bias investigation. Unlike text-based models, which encode gendered associations implicitly, Speech-LLMs must produce a gendered voice, making speaker selection an explicit bias cue. We evaluate Bark, a Text-to-Speech (TTS) model, analyzing its default speaker assignments for textual prompts. If Bark's speaker selection systematically aligns with gendered associations, it may reveal patterns in its training data or model design. To test this, we construct two datasets: (i) Professions, containing gender-stereotyped occupations, and (ii) Gender-Colored Words, featuring gendered connotations. While Bark does not exhibit systematic bias, it demonstrates gender awareness and has some gender inclinations.

While reinforcement learning (RL) is gaining popularity in gameplay, creating a generalized RL model is still challenging. This study presents BaziGooshi, a generalized RL solution for games, focusing on two different types of games: 1) a puzzle game Candy Crush Friends Saga and 2) a platform game Sonic the Hedgehog Genesis. BaziGooshi rewards RL agents for mastering a set of intrinsic basic skills as well as achieving the game objectives. The solution includes a hybrid model that takes advantage of a combination of several agents pretrained using intrinsic or extrinsic rewards to determine the actions. We propose an RL-based method for assigning weights to the pretrained agents. Through experiments, we show that the RL-based approach improves generalization to unseen levels, and BaziGooshi surpasses the performance of most of the defined baselines in both games. Also, we perform additional experiments to investigate further the impacts of using intrinsic rewards and the effects of using different combinations in the proposed hybrid models.

Training of deep neural networks from scratch requires initialization of the neural network weights as a first step. Over the years, many policies and techniques for weight initialization have been proposed and widely used, including Kaiming initialization and different variants of random initialization. On the other hand, another requirement for starting the training stage is to choose and set suitable hyperparameter values, which are usually obtained by performing several hyperparameter tuning trials. In this paper, we study the suitability of weight initialization using weights obtained from different epochs of hyperparameter tuning trials and compare it to Kaiming uniform (random) weight initialization for image classification tasks. Based on an experimental evaluation using ResNet-18, ResNet-152, and InceptionV3 models, and CIFAR-10, CIFAR-100, Tiny ImageNet, and Food-101 datasets, we show that weight initialization from hyperparameter tuning trials can speed up the training of deep neural networks by up to 2x while maintaining or improving the best test accuracy of the trained models, when compared to random initialization.