Artificial Intelligence and Robotics Commons^™

Xfinbench: Benchmarking Llms In Complex Financial Problem Solving And Reasoning, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Solving financial problems demands complex reasoning, multimodal data processing, and a broad technical understanding, presenting unique challenges for current large language models (LLMs). We introduce **XFinBench**, a novel benchmark with 4,235 examples designed to evaluate LLM’s ability in solving comple**X**, knowledge-intensive **Fin**ancial problems across diverse graduate-level finance topics with multi-modal context. We identify five core capabilities of LLMs using XFinBench, i.e., _terminology understanding_, _temporal reasoning_, _future forecasting_, _scenario planning_, and _numerical modelling_. Upon XFinBench, we conduct extensive experiments on 18 leading models. The result shows that o1 is the best-performing text-only model with an overall accuracy of 67.3%, but still …

Memotune: A Measure And Moment-Driven Fine-Tuning Framework For Quantized Large Language Models, Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu

Research Collection School Of Computing and Information Systems

Quantizing large language models (LLMs) is essential for reducing memory and computational costs in natural language processing. Existing methods combine quantization with parameter-efficient fine-tuning but often fail to meet practical performance requirements. This paper introduces MeMoTune, a novel fine-tuning framework for quantized LLMs. By employing a measure and moment approach within a low-rank approximation framework in probability measure space, MeMoTune optimizes the objective function for superior fine-tuning results. The update process is further refined through scaled gradient, enhancing convergence efficiency and noise robustness. Experiments on tasks like text generation, summarization, and understanding show MeMoTune significantly outperforms state-of-the-art methods, e.g. fine-tuning …

How To Enable Effective Cooperation Between Humans And Nlp Models: A Survey Of Principles, Formalizations, And Beyond, Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua, Jimmy Huang

Research Collection School Of Computing and Information Systems

With the advancement of large language models (LLMs), intelligent models have evolved from mere tools to autonomous agents with their own goals and strategies for cooperating with humans. This evolution has birthed a novel paradigm in NLP, i.e., human-model cooperation, that has yielded remarkable progress in numerous NLP tasks in recent years. In this paper, we take the first step to present a thorough review of human-model cooperation, exploring its principles, formalizations, and open challenges. In particular, we introduce a new taxonomy that provides a unified perspective to summarize existing approaches. Also, we discuss potential frontier areas and their corresponding …

Evowiki: Evaluating Llms On Evolving Knowledge, Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao

Research Collection School Of Computing and Information Systems

Knowledge utilization is a critical aspect of LLMs, and understanding how they adapt to evolving knowledge is essential for their effective deployment. However, existing benchmarks are predominantly static, failing to capture the evolving nature of LLMs and knowledge, leading to inaccuracies and vulnerabilities such as contamination. In this paper, we introduce EvoWiki, an evolving dataset designed to reflect knowledge evolution by categorizing information into stable, evolved, and uncharted states. EvoWiki is fully auto-updated, enabling precise evaluation of continuously changing knowledge and newly released LLMs. Through experiments with Retrieval-Augmented Generation (RAG) and Continual Learning (CL), we evaluate how effectively LLMs adapt …

Llm2rec: Large Language Models Are Powerful Embedding Models For Sequential Recommendation, Yingzhi He, Xiaohao Liu, An Zhang, Yunshan Ma, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Sequential recommendation aims to predict users' future interactions by modeling collaborative filtering (CF) signals from historical behaviors of similar users or items. Traditional sequential recommenders predominantly rely on ID-based embeddings, which capture CF signals through high-order co-occurrence patterns. However, these embeddings depend solely on past interactions, lacking transferable knowledge to generalize to unseen domains. Recent advances in large language models (LLMs) have motivated text-based recommendation approaches that derive item representations from textual descriptions. While these methods enhance generalization, they fail to encode CF signals-i.e., latent item correlations and preference patterns-crucial for effective recommendation. We argue that an ideal embedding model …

Debate, Reflect, And Distill: Multi-Agent Feedback With Tree-Structured Preference Optimization For Efficient Language Model Enhancement, Xiaofeng Zhou, Heyan Huang, Lizi Liao

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a sustainable solution, current techniques—such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection—struggle to yield substantial and lasting performance gains. In this paper, we present a novel Debate and Reflect (D&R) framework that orchestrates multi-turn debates between smaller models and stronger teacher models, eliciting actionable feedback (e.g., error analysis, corrective strategies) to guide student models. Further, we introduce Tree-structured Direct Preference Optimization (T-DPO) to …

The Impact Of Artificial Intelligence As An Intervening Variable Between The Digital Government Strategy And Competency Development "An Applied Study At Sharjah Police Sciences Academy ", Elsayed Kamal Risha, Abd Al-Rahman Al-Naqbi

Journal of Police and Legal Sciences

The study aimed to determine the impact of the digital government strategy on competencies development, through artificial intelligence as an intervening variable, and to achieve the objectives, the study relied on the quantitative approach and the questionnaire was used as the main tool for collecting data. The study community represented officers, non-commissioned officers and individuals at the Sharjah Academy for Police Sciences, and the study sample amounted to 30 affiliates, i.e. the total number of employees in the Competency Development Department at the Academy. The study reached a set of results, the most prominent of which are:

- The existence …

Query Understanding In Llm-Based Conversational Information Seeking, Yifei Yuan, Zahra Abbasiantaeb, Mohammad Aliannejadi, Yang Deng

Research Collection School Of Computing and Information Systems

Query understanding in CIS involves accurately interpreting user intent through context-aware interactions. This includes resolving ambiguities, refining queries, and adapting to evolving information needs. LLM enhance this process by interpreting nuanced language and adapting dynamically, improving the relevance and precision of search results in real-time. In this tutorial, we explore advanced techniques to enhance query understanding in LLM-based CIS systems. We delve into LLM-driven methods for developing robust evaluation metrics to assess query understanding quality in multi-turn interactions, strategies for building more interactive systems, and applications like proactive query management and query reformulation. We also discuss key challenges in integrating …

Milpbench: A Large-Scale Benchmark Test Suite For Mixed Integer Linear Programming Problems, Huigen Ye, Yaoyang Cheng, Hua Xu, Zhiguang Cao, Hanzhang Qin

Research Collection School Of Computing and Information Systems

Mixed-integer linear programming (MILP) is a cornerstone of optimization with applications across numerous domains. However, the development and evaluation of MILP-solving algorithms are hindered by existing benchmark datasets, which are often limited in scale, lack diversity, and are poorly structured, making them inadequate for systematic testing across different solving approaches, especially for machine learning (ML)-based methods. To address these issues, we introduce MILPBench, a large-scale benchmark suite comprising 100,000 MILP instances organized into 60 well-categorized classes. Using structural properties and embedding similarity metrics, we developed a novel classification framework to ensure both intra-class homogeneity and inter-class diversity. In addition to …

Learning And Optimization Under Human-Centric Considerations, Qian Shao

Dissertations and Theses Collection (Open Access)

This dissertation investigates learning and optimization problems shaped by humancentric considerations, such as preferences, demonstrations, behavioral patterns, and resource constraints. As real-world decision-making increasingly involves interaction with human agents, data, and limitations, modeling these factors becomes critical for building practical, adaptive, and robust systems.

The research spans four domains. First, we study preference-aware delivery routing by learning implicit practitioner preferences and incorporating them into a hierarchical route optimization framework. Second, we develop imitation learning methods for cost-constrained settings, enabling agents to mimic expert behavior while respecting safety and resource limitations. Third,we explore early rumor detection in data-limited environments, integrating large …

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the “best of both worlds,” using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the “best of both worlds,” using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Comparative Analysis Of Classical And Machine Learning Pathfinding Approaches, Miguel Gapud

Honors Theses

Pathfinding is an essential task for any autonomous robot. Graph-based classical pathfinding algorithms and machine learning approaches have both been used for this end, but they are often not compared against each other. An implementation of end-to-end (E2E) pathfinding using Proximal Policy Optimization (PPO) and an Alexnet architecture is compared against an implementation of Hybrid A*. A digital twin in Unity3D is used as the testing environment with the Clearpath Dingo as the pathfinding robot. In machine learning, the robot is controlled using PPO through ROS-Noetic with a camera as its sensor. Hybrid A* and its controls are implemented directly …

Hello Again! Llm-Powered Personalized Agent For Long-Term Dialogue, Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the real-world demands for long-term companionship and personalized interactions with chatbots. Crucial to addressing this real-world need are event summary and persona management, which enable reasoning for appropriate long-term dialogue responses. Recent progress in the human-like cognitive and reasoning capabilities of LLMs suggests that LLM-based agents could significantly enhance automated perception, decision-making, and problem-solving. In response to this potential, we introduce a model-agnostic framework, the Long-term Dialogue Agent (LD-Agent), which incorporates three independently …

Reverse Modeling In Large Language Models, Sicheng Yu, Yuanchen Xu, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu

Research Collection School Of Computing and Information Systems

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse modeling, specifically with reversed text inputs. We found that publicly available pre-trained LLMs cannot understand such inputs. However, LLMs trained from scratch with both forward and reverse texts can understand them equally well during inference. Our case study shows that different-content texts result in different losses if input (to LLMs) in different directions---some get lower losses for forward while some for reverse. This leads us …

Coding An Assignment Calculator Exclusively With Chatgpt, Andy Tincknell, Heather P. Vandyne, Lisa K. Bell

SACAD: Scholarly Activities

Large Language Models like ChatGPT are influencing higher education and society in broader ways, including the coding and programming of applications and websites (Silva et al., 2024). This poster will profile how Forsyth Library, with no coders on staff, used ChatGPT to program an Assignment Calculator LibGuide without human coding. It details the process, challenges, and outcomes while highlighting AI’s potential to enhance resources for academic success and considers its efficacy and ethical implications.

Frame-Voyager: Learning To Query Frames For Video Large Language Models, Sicheng Yu, Chengkai Jin, Huanyu Wang, Zhenghao Chen, Sheng Jin, Zhongrong Zuo, Xiaolei Xu, Zhenbang Sun, Bingni Zhang, Jiawei Wu, Hao Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection approaches, such as uniform frame sampling and text-frame retrieval, fail to account for the information density variations in the videos or the complex instructions in the tasks, leading to sub-optimal performance. In this paper, we propose Frame-Voyager that learns to query informative frame combinations, based on the given textual queries in the task. To train Frame-Voyager, we introduce a new data collection and labeling pipeline, by …

Bootstrapping Language Models With Dpo Implicit Rewards, Changyu Chen, Zichen Liu, Chao Du, Tianyu Pang, Qian Liu, Arunesh Sinha, Pradeep Varakantham, Min Lin

Research Collection School Of Computing and Information Systems

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human feedback (RLHF) by bypassing the reward learning stage in RLHF. DPO, after training, provides an implicit reward model. In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM. Our approach is to use the rewards from a current LLM model to construct a preference dataset, which is then used …

Chatcrs: Incorporating External Knowledge And Goal Guidance For Llm-Based Conversational Recommender Systems, Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li

Research Collection School Of Computing and Information Systems

This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into …

Alphaedit: Null-Space Constrained Knowledge Editing For Language Models, Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) often exhibit hallucinations, producing incorrector outdated knowledge. Hence, model editing methods have emerged to enabletargeted knowledge updates. To achieve this, a prevailing paradigm is the locatingthen-editing approach, which first locates influential parameters and then edits themby introducing a perturbation. While effective, current studies have demonstrated that this perturbation inevitably disrupt the originally preserved knowledge within LLMs, especially in sequential editing scenarios. To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters. We theoretically prove that this projection ensures the output …

Adversarial Attacks And Defense Methods In Robotic Systems, Thanh D. Le

Shelby Hall Graduate Research Forum Presentations

Presentation slides for a presentation given at the 1st annual Shelby Hall Graduate Research Forum at the University of South Alabama.

Choosing Robust Leadership: Encompassing The Best-Of-N Model And Swarm Intelligence Optimization For Heterogeneous Multiple Autonomous Unmanned Aerial Vehicle Systems, Kudamuhandiramlage Harith Kolitha Warnakulasooriya

Shelby Hall Graduate Research Forum Presentations

Presentation slides for a presentation given at the 1st annual Shelby Hall Graduate Research Forum at the University of South Alabama.

Attackg+: Boosting Attack Graph Construction With Large Language Models, Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee‑Chien Chang

Research Collection School Of Computing and Information Systems

Attack graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structuredrepresentations, portraying the evolutionary traces of cyber attacks. Even though previous research hasproposed various methods to construct attack graphs, they generally suffer from limited generalizationcapability to diverse knowledge types as well as requirement of expertise in model design and tuning.Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormoussuccess in a broad range of tasks given exceptional capabilities in both language understanding and zeroshot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack graphsnamed: AttacKG+. Our framework consists …

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin

Research Collection School Of Computing and Information Systems

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern …

Towards Smart Farming: Image-Based Crop Health Assessment And Disease Diagnosis Using Deep Learning Techniques, Kristina Botova

Master's Theses or Doctor of Nursing Practice

Accurate crop monitoring is essential for optimizing agricultural productivity and ensuring food security. This study presents a comprehensive deep learning framework for image crop type recognition, health status prediction, and disease detection using multiple Convolutional Neural Network (CNN) models. The proposed approach uses open-source datasets consisting of five crop types (apple, corn, grape, potato, tomato), varying health conditions, and common diseases. By deploying specialized CNN architecture focused on each task, the system achieves a high accuracy of 99.25% in classifying crop types, identifying health status, and detecting specific diseases. Compared to a single CNN model, the use of the proposed …

Digital Platform Transitions In The Finance Industry: Three Essays, Cheryll-Ann Wilson

2025

This three-paper dissertation is motivated by an emerging dichotomy in the financial sector: an increasing use of an open-source digital platform—the Python platform—in an industry that historically has been wedded to proprietary systems.

Chapter 1 is a qualitative pilot study to ascertain which factors are likely to motivate investment professionals to select Python versus other tools and/or technologies. I find that efficiency and access to industry-specific libraries—notably Pandas and NumPy—are significant motivators in their selection of Python over Excel. Chapters 2 and 3 examine the issues through a sequential, exploratory mixed methods approach.

Chapter 2—the qualitative field study—investigates how and …

Financial Named Entity Recognition: How Far Can Llm Go?, Yi-Te Lu, Yintong Huo

Research Collection School Of Computing and Information Systems

The surge of large language models (LLMs) has revolutionized the extraction and analysis of crucial information from a growing volume of financial statements, announcements, and business news. Recognition for named entities to construct structured data poses a significant challenge in analyzing financial documents and is a foundational task for intelligent financial analytics. However, how effective are these generic LLMs and their performance under various prompts are yet need a better understanding. To fill in the blank, we present a systematic evaluation of state-of-the-art LLMs and prompting methods in the financial Named Entity Recognition (NER) problem. Specifically, our experimental results highlight …

Reevo: Large Language Models As Hyper-Heuristics With Reflective Evolution, Haoran Ye, Jiarui Wang, Zhiguang Cao, Federico Berto, Chuanbo Hua, Haeyeon Kim, Jinkyoo Park, Guojie Song

Research Collection School Of Computing and Information Systems

The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design process. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a generic searching framework that emulates the reflective design approach of human experts while far surpassing human capabilities with its scalable LLM inference, Internet-scale domain knowledge, and powerful evolutionary search. Evaluations …

Mm‑Forecast: A Multimodal Approach To Temporal Event Forecasting With Large Language Models, Haoxuan Li, Zhengmao Yang, Yunshan Ma, Yi Bin, Yang Yang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

We study an emerging and intriguing problem of multimodal temporal event forecasting with large language models. Compared to using text or graph modalities, the investigation of utilizing images for temporal event forecasting has not been fully explored, especially in the era of large language models (LLMs). To bridge this gap, we are particularly interested in two key questions of: 1) why images will help in temporal event forecasting, and 2) how to integrate images into the LLM-based forecasting framework. To answer these research questions, we propose to identify two essential functions that images play in the scenario of temporal event …