This systematic review explores the application of Large Language Models (LLMs) in Combinatorial Optimization (CO). We report our findings using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We conduct a literature search via Scopus and Google Scholar, examining over 2,000 publications. We assess publications against four inclusion and four exclusion criteria related to their language, research focus, publication year, and type. Eventually, we select 103 studies. We classify these studies into semantic categories and topics to provide a comprehensive overview of the field, including the tasks performed by LLMs, the architectures of LLMs, the existing datasets specifically designed for evaluating LLMs in CO, and the field of application. Finally, we identify future directions for leveraging LLMs in this field.

The robust and accurate recognition of multicultural names, particularly those not previously encountered, is a critical challenge in an increasingly globalized digital landscape. Traditional methods often falter when confronted with the vast diversity and novel permutations of names across different linguistic and cultural backgrounds. This paper introduces a novel framework, Prompt-Engineered Fine-Tuning (PEFT) for Large Language Models (LLMs) with Adversarial Data Augmentation and Cultural Knowledge Graph Integration, designed to significantly enhance zero-shot multicultural name recognition. Our approach leverages the powerful linguistic understanding of pre-trained LLMs, transforming the recognition task into a guided generation problem. Through meticulous prompt engineering, dynamic integration of explicit cultural knowledge derived from knowledge graphs, and the strategic application of adversarial data augmentation, we equip the LLM with an unprecedented ability to infer the cultural origin of unseen names. Extensive experiments demonstrate that our PEFT method consistently outperforms established deep learning baselines, including advanced Bi-LSTM models with cultural tags, achieving an impressive 93.1\% overall accuracy and a remarkable 89.5\% accuracy on challenging zero-shot name identification. An in-depth ablation study confirms the synergistic contribution of each component, while a human evaluation highlights our method's performance approaching human expert judgment. This work signifies a substantial leap in multicultural name recognition, offering a highly effective and scalable solution for real-world applications.

Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented generation (RAG) framework designed to facilitate UGI. Central to UrbanMind is a novel architecture based on Continual Retrieval-Augmented MoE-based LLM (C-RAG-LLM), which dynamically incorporates domain-specific knowledge and evolving urban data to support long-term adaptability. The architecture of C-RAG-LLM aligns naturally with a multilevel optimization framework, where different layers are treated as interdependent sub-problems. Each layer has distinct objectives and can be optimized either independently or jointly through a hierarchical learning process. The framework is highly flexible, supporting both end-to-end training and partial layer-wise optimization based on resource or deployment constraints. To remain adaptive under data drift, it is further integrated with an incremental corpus updating mechanism. Evaluations on real-world urban tasks of a variety of complexity verify the effectiveness of the proposed framework. This work presents a promising step toward the realization of general-purpose LLM agents in future urban environments.

This article introduces semantically meaningful causal language modeling (SMCLM), a selfsupervised method of training autoregressive models to generate semantically equivalent text. Our approach involves using semantically meaningful text representation as an initial embedding in the autoregressive training and generation processes. The extensive empirical study demonstrates that the SMCLM approach makes autoregressive models capable of learning robust and high-quality paraphrase generation. The proposed method is competitive with the supervised method and achieves state-of-the-art results in unsupervised approaches. This article also presents a comprehensive set of automatic metrics that cover a wide range of autogenerated paraphrase evaluation aspects. Simultaneously, this article highlights the low reliability of the metrics that are widely used in paraphrase generation evaluation, including BLEU, ROUGE, and BERTScore.

Task-oriented dialogue (TOD) systems facilitate goal-driven interactions between users and machines. While recent advances in deep learning have improved the performance, TOD systems often struggle in low-resource scenarios with limited labeled data. To address this challenge, we propose Spec-TOD, a novel framework designed to train an end-to-end TOD system with limited data. Spec-TOD introduces two main innovations: (i) a novel specialized end-to-end TOD framework that incorporates explicit task instructions for instruction-tuned large language models (LLMs), and (ii) an efficient training strategy that leverages lightweight, specialized LLMs to achieve strong performance with minimal supervision. Experiments on the MultiWOZ dataset, a widely used TOD benchmark, demonstrate that Spec-TOD achieves competitive results while significantly reducing the need for labeled data. These findings highlight the potential of the proposed framework in advancing efficient and effective TOD systems in low-resource settings.

The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in recent years, and yet there is no standard, widely accepted method for the constrained training of DNNs. In this paper, we provide a challenging benchmark of real-world large-scale fairness-constrained learning tasks, built on top of the US Census (Folktables). We point out the theoretical challenges of such tasks and review the main approaches in stochastic approximation algorithms. Finally, we demonstrate the use of the benchmark by implementing and comparing three recently proposed, but as-of-yet unimplemented, algorithms both in terms of optimization performance, and fairness improvement. We release the code of the benchmark as a Python package at https://github.com/humancompatible/train.

Large Language Models (LLMs) continue to advance natural language processing with their ability to generate human-like text across a range of tasks. Despite the remarkable success of LLMs in Natural Language Processing (NLP), their performance in text summarization across various domains and datasets has not been comprehensively evaluated. At the same time, the ability to summarize text effectively without relying on extensive training data has become a crucial bottleneck. To address these issues, we present a systematic evaluation of six LLMs across four datasets: CNN/Daily Mail and NewsRoom (news), SAMSum (dialog), and ArXiv (scientific). By leveraging prompt engineering techniques including zero-shot and in-context learning, our study evaluates the performance using the ROUGE and BERTScore metrics. In addition, a detailed analysis of inference times is conducted to better understand the trade-off between summarization quality and computational efficiency. For Long documents, introduce a sentence-based chunking strategy that enables LLMs with shorter context windows to summarize extended inputs in multiple stages. The findings reveal that while LLMs perform competitively on news and dialog tasks, their performance on long scientific documents improves significantly when aided by chunking strategies. In addition, notable performance variations were observed based on model parameters, dataset properties, and prompt design. These results offer actionable insights into how different LLMs behave across task types, contributing to ongoing research in efficient, instruction-based NLP systems.

This paper describes our research on AI agents embodied in visual, virtual or physical forms, enabling them to interact with both users and their environments. These agents, which include virtual avatars, wearable devices, and robots, are designed to perceive, learn and act within their surroundings, which makes them more similar to how humans learn and interact with the environments as compared to disembodied agents. We propose that the development of world models is central to reasoning and planning of embodied AI agents, allowing these agents to understand and predict their environment, to understand user intentions and social contexts, thereby enhancing their ability to perform complex tasks autonomously. World modeling encompasses the integration of multimodal perception, planning through reasoning for action and control, and memory to create a comprehensive understanding of the physical world. Beyond the physical world, we also propose to learn the mental world model of users to enable better human-agent collaboration.

Recent advancements in graph diffusion models (GDMs) have enabled the synthesis of realistic network structures, yet ensuring fairness in the generated data remains a critical challenge. Existing solutions attempt to mitigate bias by re-training the GDMs with ad-hoc fairness constraints. Conversely, with this work, we propose FAROS, a novel FAir graph geneRatiOn framework leveraging attribute Switching mechanisms and directly running in the generation process of the pre-trained GDM. Technically, our approach works by altering nodes' sensitive attributes during the generation. To this end, FAROS calculates the optimal fraction of switching nodes, and selects the diffusion step to perform the switch by setting tailored multi-criteria constraints to preserve the node-topology profile from the original distribution (a proxy for accuracy) while ensuring the edge independence on the sensitive attributes for the generated graph (a proxy for fairness). Our experiments on benchmark datasets for link prediction demonstrate that the proposed approach effectively reduces fairness discrepancies while maintaining comparable (or even higher) accuracy performance to other similar baselines. Noteworthy, FAROS is also able to strike a better accuracy-fairness trade-off than other competitors in some of the tested settings under the Pareto optimality concept, demonstrating the effectiveness of the imposed multi-criteria constraints.

Edgar Allan Poe noted, "Truth often lurks in the shadow of error," highlighting the deep complexity intrinsic to the interplay between truth and falsehood, notably under conditions of cognitive and informational asymmetry. This dynamic is strikingly evident in large language models (LLMs). Despite their impressive linguistic generation capabilities, LLMs sometimes produce information that appears factually accurate but is, in reality, fabricated, an issue often referred to as 'hallucinations'. The prevalence of these hallucinations can mislead users, affecting their judgments and decisions. In sectors such as finance, law, and healthcare, such misinformation risks causing substantial economic losses, legal disputes, and health risks, with wide-ranging consequences.In our research, we have methodically categorized, analyzed the causes, detection methods, and solutions related to LLM hallucinations. Our efforts have particularly focused on understanding the roots of hallucinations and evaluating the efficacy of current strategies in revealing the underlying logic, thereby paving the way for the development of innovative and potent approaches. By examining why certain measures are effective against hallucinations, our study aims to foster a comprehensive approach to tackling this issue within the domain of LLMs.