Lingbo Li

Peng Liao, Peijia Zheng, Lingbo Li et al.

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods typically involves additional hyperparameter tuning, resulting in substantial time overhead. Although prior work has proposed a range of improvements, these methods remain limited in effectiveness and have not fully eliminated reliance on hyperparameter tuning. In this work, we propose RMiPO, a lightweight and efficient framework for offline preference optimization. RMiPO leverages intrinsic Response-level Mutual information for Preference Optimization with hyperparameter modulation, dynamically decoupling preference contributions at negligible additional computational cost. Extensive experimental results demonstrate that RMiPO achieves consistently superior performance over existing methods while reducing training overhead by more than 15\%. Our code is available at https://github.com/liavonpenn/rmipo.

Lingbo Li, Anuradha Mathrani, Teo Susnjak

Assessing risk of bias (RoB) in randomized controlled trials is essential for trustworthy evidence synthesis, but the process is resource-intensive and prone to variability across reviewers. Large language models (LLMs) offer a route to automation, but existing methods rely on manually engineered prompts that are difficult to reproduce, generalize, or evaluate. This study introduces a programmable RoB assessment pipeline that replaces ad-hoc prompt design with structured, code-based optimization using DSPy and its GEPA module. GEPA refines LLM reasoning through Pareto-guided search and produces inspectable execution traces, enabling transparent replication of every step in the optimization process. We evaluated the method on 100 RCTs from published meta-analyses across seven RoB domains. GEPA-generated prompts were applied to both open-weight models (Mistral Small 3.1 with GPT-oss-20b) and commercial models (GPT-5 Nano and GPT-5 Mini). In domains with clearer methodological reporting, such as Random Sequence Generation, GEPA-generated prompts performed best, with similar results for Allocation Concealment and Blinding of Participants, while the commercial model performed slightly better overall. We also compared GEPA with three manually designed prompts using Claude 3.5 Sonnet. GEPA achieved the highest overall accuracy and improved performance by 30%-40% in Random Sequence Generation and Selective Reporting, and showed generally comparable, competitively aligned performance in the other domains relative to manual prompts. These findings suggest that GEPA can produce consistent and reproducible prompts for RoB assessment, supporting the structured and principled use of LLMs in evidence synthesis.

Lingbo Li, Tianle Li, Xinyi He et al.

Intelligent analysis and visualization of tables use techniques to automatically recommend useful knowledge from data, thus freeing users from tedious multi-dimension data mining. While many studies have succeeded in automating recommendations through rules or machine learning, it is difficult to generalize expert knowledge and provide explainable recommendations. In this paper, we present the recommendation of conditional formatting for the first time, together with chart recommendation, to exemplify intelligent table analysis. We propose analytical semantics over tables to uncover common analysis pattern behind user-created analyses. Here, we design analytical semantics by separating data focus from user intent, which extract the user motivation from data and human perspective respectively. Furthermore, the ASTA framework is designed by us to apply analytical semantics to multiple automated recommendations. ASTA framework extracts data features by designing signatures based on expert knowledge, and enables data referencing at field- (chart) or cell-level (conditional formatting) with pre-trained models. Experiments show that our framework achieves recall at top 1 of 62.86% on public chart corpora, outperforming the best baseline about 14%, and achieves 72.31% on the collected corpus ConFormT, validating that ASTA framework is effective in providing accurate and explainable recommendations.

Zijun Gao, Haibao Liu, Lingbo Li

Data Augmentation (DA) has become a critical approach in Time Series Classification (TSC), primarily for its capacity to expand training datasets, enhance model robustness, introduce diversity, and reduce overfitting. However, the current landscape of DA in TSC is plagued with fragmented literature reviews, nebulous methodological taxonomies, inadequate evaluative measures, and a dearth of accessible and user-oriented tools. This study addresses these challenges through a comprehensive examination of DA methodologies within the TSC domain.Our research began with an extensive literature review spanning a decade, revealing significant gaps in existing surveys and necessitating a detailed analysis of over 100 scholarly articles to identify more than 60 distinct DA techniques. This rigorous review led to the development of a novel taxonomy tailored to the specific needs of DA in TSC, categorizing techniques into five primary categories: Transformation-Based, Pattern-Based, Generative, Decomposition-Based, and Automated Data Augmentation. This taxonomy is intended to guide researchers in selecting appropriate methods with greater clarity. In response to the lack of comprehensive evaluations of foundational DA techniques, we conducted a thorough empirical study, testing nearly 20 DA strategies across 15 diverse datasets representing all types within the UCR time-series repository. Using ResNet and LSTM architectures, we employed a multifaceted evaluation approach, including metrics such as Accuracy, Method Ranking, and Residual Analysis, resulting in a benchmark accuracy of 84.98 +- 16.41% in ResNet and 82.41 +- 18.71% in LSTM. Our investigation underscored the inconsistent efficacies of DA techniques, for instance, methods like RGWs and Random Permutation significantly improved model performance, whereas others, like EMD, were less effective.

Lingbo Li, Leslie Kanthan, Michail Basios et al.

Machine learning model development and optimisation can be a rather cumbersome and resource-intensive process. Custom models are often more difficult to build and deploy, and they require infrastructure and expertise which are often costly to acquire and maintain. Machine learning product development lifecycle must take into account the need to navigate the difficulties of developing and deploying machine learning models. evoML is an AI-powered tool that provides automated functionalities in machine learning model development, optimisation, and model code optimisation. Core functionalities of evoML include data cleaning, exploratory analysis, feature analysis and generation, model optimisation, model evaluation, model code optimisation, and model deployment. Additionally, a key feature of evoML is that it embeds code and model optimisation into the model development process, and includes multi-objective optimisation capabilities.

Wenjin Niu, Zijun Gao, Liyan Song et al.

Causal analysis has become an essential component in understanding the underlying causes of phenomena across various fields. Despite its significance, existing literature on causal discovery algorithms is fragmented, with inconsistent methodologies, i.e., there is no universal classification standard for existing methods, and a lack of comprehensive evaluations, i.e., data characteristics are often ignored to be jointly analyzed when benchmarking algorithms. This study addresses these gaps by conducting an exhaustive review and empirical evaluation for causal discovery methods on numerical data, aiming to provide a clearer and more structured understanding of the field. Our research begins with a comprehensive literature review spanning over two decades, analyzing over 200 academic articles and identifying more than 40 representative algorithms. This extensive analysis leads to the development of a structured taxonomy tailored to the complexities of causal discovery, categorizing methods into six main types. To address the lack of comprehensive evaluations, our study conducts an extensive empirical assessment of 29 causal discovery algorithms on multiple synthetic and real-world datasets. We categorize synthetic datasets based on size, linearity, and noise distribution, employing five evaluation metrics, and summarize the top-3 algorithm recommendations, providing guidelines for users in various data scenarios. Our results highlight a significant impact of dataset characteristics on algorithm performance. Moreover, a metadata extraction strategy with an accuracy exceeding 80% is developed to assist users in algorithm selection on unknown datasets. Based on these insights, we offer professional and practical guidelines to help users choose the most suitable causal discovery methods for their specific dataset.

Gongbo Zhang, Yanting Li, Renqian Luo et al. · microsoft-research

Function in natural systems arises from one-dimensional sequences forming three-dimensional structures with specific properties. However, current generative models suffer from critical limitations: training objectives seldom target function directly, discrete sequences and continuous coordinates are optimized in isolation, and conformational ensembles are under-modeled. We present UniGenX, a unified generative foundation model that addresses these gaps by co-generating sequences and coordinates under direct functional and property objectives across proteins, molecules, and materials. UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens, where a decoder-only autoregressive transformer provides global context and a conditional diffusion head generates numeric fields steered by task-specific tokens. Besides the new high SOTAs on structure prediction tasks, the model demonstrates state-of-the-art or competitive performance for the function-aware generation across domains: in materials, it achieves "conflicted" multi-property conditional generation, yielding 436 crystal candidates meeting triple constraints, including 11 with novel compositions; in chemistry, it sets new benchmarks on five property targets and conformer ensemble generation on GEOM; and in biology, it improves success in modeling protein induced fit (RMSD < 2 Å) by over 23-fold and enhances EC-conditioned enzyme design. Ablation studies and cross-domain transfer substantiate the benefits of joint discrete-continuous training, establishing UniGenX as a significant advance from prediction to controllable, function-aware generation.

Lingbo Li, Anuradha Mathrani, Teo Susnjak

Exponential growth in scientific literature has heightened the demand for efficient evidence-based synthesis, driving the rise of the field of Automated Meta-analysis (AMA) powered by natural language processing and machine learning. This PRISMA systematic review introduces a structured framework for assessing the current state of AMA, based on screening 978 papers from 2006 to 2024, and analyzing 54 studies across diverse domains. Findings reveal a predominant focus on automating data processing (57%), such as extraction and statistical modeling, while only 17% address advanced synthesis stages. Just one study (2%) explored preliminary full-process automation, highlighting a critical gap that limits AMA's capacity for comprehensive synthesis. Despite recent breakthroughs in large language models (LLMs) and advanced AI, their integration into statistical modeling and higher-order synthesis, such as heterogeneity assessment and bias evaluation, remains underdeveloped. This has constrained AMA's potential for fully autonomous meta-analysis. From our dataset spanning medical (67%) and non-medical (33%) applications, we found that AMA has exhibited distinct implementation patterns and varying degrees of effectiveness in actually improving efficiency, scalability, and reproducibility. While automation has enhanced specific meta-analytic tasks, achieving seamless, end-to-end automation remains an open challenge. As AI systems advance in reasoning and contextual understanding, addressing these gaps is now imperative. Future efforts must focus on bridging automation across all meta-analysis stages, refining interpretability, and ensuring methodological robustness to fully realize AMA's potential for scalable, domain-agnostic synthesis.

Lingbo Li, Anuradha Mathrani, Teo Susnjak

Automating data extraction from full-text randomised controlled trials (RCTs) for meta-analysis remains a significant challenge. This study evaluates the practical performance of three LLMs (Gemini-2.0-flash, Grok-3, GPT-4o-mini) across tasks involving statistical results, risk-of-bias assessments, and study-level characteristics in three medical domains: hypertension, diabetes, and orthopaedics. We tested four distinct prompting strategies (basic prompting, self-reflective prompting, model ensemble, and customised prompts) to determine how to improve extraction quality. All models demonstrate high precision but consistently suffer from poor recall by omitting key information. We found that customised prompts were the most effective, boosting recall by up to 15\%. Based on this analysis, we propose a three-tiered set of guidelines for using LLMs in data extraction, matching data types to appropriate levels of automation based on task complexity and risk. Our study offers practical advice for automating data extraction in real-world meta-analyses, balancing LLM efficiency with expert oversight through targeted, task-specific automation.

Ruiyan Qi, Congding Wen, Weibo Zhou et al.

Evaluating large language models (LLMs) in specific domain like tourism remains challenging due to the prohibitive cost of annotated benchmarks and persistent issues like hallucinations. We propose $\textbf{L}$able-Free $\textbf{E}$valuation of LLM on $\textbf{T}$ourism using Expert $\textbf{T}$ree-$\textbf{o}$f-$\textbf{T}$hought (LETToT), a framework that leverages expert-derived reasoning structures-instead of labeled data-to access LLMs in tourism. First, we iteratively refine and validate hierarchical ToT components through alignment with generic quality dimensions and expert feedback. Results demonstrate the effectiveness of our systematically optimized expert ToT with 4.99-14.15\% relative quality gains over baselines. Second, we apply LETToT's optimized expert ToT to evaluate models of varying scales (32B-671B parameters), revealing: (1) Scaling laws persist in specialized domains (DeepSeek-V3 leads), yet reasoning-enhanced smaller models (e.g., DeepSeek-R1-Distill-Llama-70B) close this gap; (2) For sub-72B models, explicit reasoning architectures outperform counterparts in accuracy and conciseness ($p<0.05$). Our work established a scalable, label-free paradigm for domain-specific LLM evaluation, offering a robust alternative to conventional annotated benchmarks.

Weibo Zhou, Lingbo Li, Shangsong Liang

The scarcity and high cost of high-quality question-answering (QA) datasets hinder supervised fine-tuning (SFT) for domain-specific large language models (LLMs). To address this, we introduce D-SCoRE, a training-free pipeline that utilizes LLMs and prompt engineering to produce diverse, high-quality QA datasets from arbitrary textual sources. D-SCoRE integrates $\textbf{D}$ocument-centric processing, $\textbf{S}$egmentation, $\textbf{Co}$T $\textbf{R}$easoning, and structured $\textbf{E}$xport to generate QA-COT datasets tailored for domain-aware SFT. Multi-dimensional control mechanisms, such as semantic role transformation, question type balancing, and counterfactual materials, enhance diversity and relevance, overcoming limitations of existing QA generation. LLMs fine-tuned on D-SCoRE-generated QA datasets, and human-annotated QA datasets (SQuAD, Covid-QA) are evaluated on SQuADShifts and Covid-QA test sets, with D-SCoRE outperforming across most domains. D-SCoRE generates six QA-CoT pairs with four-option counterfactual materials per 100-200-word text in 90 seconds using an 8B LLM on consumer-grade hardware. Its simplicity and scalability enable efficient QA generation and high-performance fine-tuning across domains.

Fan Fang, Carmine Ventre, Lingbo Li et al.

Feature importance aims at measuring how crucial each input feature is for model prediction. It is widely used in feature engineering, model selection and explainable artificial intelligence (XAI). In this paper, we propose a new tree-model explanation approach for model selection. Our novel concept leverages the Coefficient of Variation of a feature weight (measured in terms of the contribution of the feature to the prediction) to capture the dispersion of importance over samples. Extensive experimental results show that our novel feature explanation performs better than general cross validation method in model selection both in terms of time efficiency and accuracy performance.

Yuxi Huan, Fan Wu, Michail Basios et al.

Hyperparameter optimisation is a crucial process in searching the optimal machine learning model. The efficiency of finding the optimal hyperparameter settings has been a big concern in recent researches since the optimisation process could be time-consuming, especially when the objective functions are highly expensive to evaluate. In this paper, we introduce an intelligent evolutionary optimisation algorithm which applies machine learning technique to the traditional evolutionary algorithm to accelerate the overall optimisation process of tuning machine learning models in classification problems. We demonstrate our Intelligent Evolutionary Optimisation (IEO)in a series of controlled experiments, comparing with traditional evolutionary optimisation in hyperparameter tuning. The empirical study shows that our approach accelerates the optimisation speed by 30.40% on average and up to 77.06% in the best scenarios.

Fan Fang, Waichung Chung, Carmine Ventre et al.

The cryptocurrency market is amongst the fastest-growing of all the financial markets in the world. Unlike traditional markets, such as equities, foreign exchange and commodities, cryptocurrency market is considered to have larger volatility and illiquidity. This paper is inspired by the recent success of using deep learning for stock market prediction. In this work, we analyze and present the characteristics of the cryptocurrency market in a high-frequency setting. In particular, we applied a deep learning approach to predict the direction of the mid-price changes on the upcoming tick. We monitored live tick-level data from $8$ cryptocurrency pairs and applied both statistical and machine learning techniques to provide a live prediction. We reveal that promising results are possible for cryptocurrencies, and in particular, we achieve a consistent $78\%$ accuracy on the prediction of the mid-price movement on live exchange rate of Bitcoins vs US dollars.

Michail Basios, Lingbo Li, Fan Wu et al.

Data structure selection and tuning is laborious but can vastly improve an application's performance and memory footprint. Some data structures share a common interface and enjoy multiple implementations. We call them Darwinian Data Structures (DDS), since we can subject their implementations to survival of the fittest. We introduce ARTEMIS a multi-objective, cloud-based search-based optimisation framework that automatically finds optimal, tuned DDS modulo a test suite, then changes an application to use that DDS. ARTEMIS achieves substantial performance improvements for \emph{every} project in $5$ Java projects from DaCapo benchmark, $8$ popular projects and $30$ uniformly sampled projects from GitHub. For execution time, CPU usage, and memory consumption, ARTEMIS finds at least one solution that improves \emph{all} measures for $86\%$ ($37/43$) of the projects. The median improvement across the best solutions is $4.8\%$, $10.1\%$, $5.1\%$ for runtime, memory and CPU usage. These aggregate results understate ARTEMIS's potential impact. Some of the benchmarks it improves are libraries or utility functions. Two examples are gson, a ubiquitous Java serialization framework, and xalan, Apache's XML transformation tool. ARTEMIS improves gson by $16.5$\%, $1\%$ and $2.2\%$ for memory, runtime, and CPU; ARTEMIS improves xalan's memory consumption by $23.5$\%. \emph{Every} client of these projects will benefit from these performance improvements.

Lingbo Li, XianXing Zhang, Mingyuan Zhou et al.

A tree-based dictionary learning model is developed for joint analysis of imagery and associated text. The dictionary learning may be applied directly to the imagery from patches, or to general feature vectors extracted from patches or superpixels (using any existing method for image feature extraction). Each image is associated with a path through the tree (from root to a leaf), and each of the multiple patches in a given image is associated with one node in that path. Nodes near the tree root are shared between multiple paths, representing image characteristics that are common among different types of images. Moving toward the leaves, nodes become specialized, representing details in image classes. If available, words (text) are also jointly modeled, with a path-dependent probability over words. The tree structure is inferred via a nested Dirichlet process, and a retrospective stick-breaking sampler is used to infer the tree depth and width.

Mingyuan Zhou, Lingbo Li, David Dunson et al.

In regression analysis of counts, a lack of simple and efficient algorithms for posterior computation has made Bayesian approaches appear unattractive and thus underdeveloped. We propose a lognormal and gamma mixed negative binomial (NB) regression model for counts, and present efficient closed-form Bayesian inference; unlike conventional Poisson models, the proposed approach has two free parameters to include two different kinds of random effects, and allows the incorporation of prior information, such as sparsity in the regression coefficients. By placing a gamma distribution prior on the NB dispersion parameter r, and connecting a lognormal distribution prior with the logit of the NB probability parameter p, efficient Gibbs sampling and variational Bayes inference are both developed. The closed-form updates are obtained by exploiting conditional conjugacy via both a compound Poisson representation and a Polya-Gamma distribution based data augmentation approach. The proposed Bayesian inference can be implemented routinely, while being easily generalizable to more complex settings involving multivariate dependence structures. The algorithms are illustrated using real examples.