Wray Buntine

Qizhou Wang, Guansong Pang, Mahsa Salehi et al.

Cross-domain graph anomaly detection (CD-GAD) describes the problem of detecting anomalous nodes in an unlabelled target graph using auxiliary, related source graphs with labelled anomalous and normal nodes. Although it presents a promising approach to address the notoriously high false positive issue in anomaly detection, little work has been done in this line of research. There are numerous domain adaptation methods in the literature, but it is difficult to adapt them for GAD due to the unknown distributions of the anomalies and the complex node relations embedded in graph data. To this end, we introduce a novel domain adaptation approach, namely Anomaly-aware Contrastive alignmenT (ACT), for GAD. ACT is designed to jointly optimise: (i) unsupervised contrastive learning of normal representations of nodes in the target graph, and (ii) anomaly-aware one-class alignment that aligns these contrastive node representations and the representations of labelled normal nodes in the source graph, while enforcing significant deviation of the representations of the normal nodes from the labelled anomalous nodes in the source graph. In doing so, ACT effectively transfers anomaly-informed knowledge from the source graph to learn the complex node relations of the normal class for GAD on the target graph without any specification of the anomaly distributions. Extensive experiments on eight CD-GAD settings demonstrate that our approach ACT achieves substantially improved detection performance over 10 state-of-the-art GAD methods. Code is available at https://github.com/QZ-WANG/ACT.

Vy Vo, Weiqing Wang, Wray Buntine

Text simplification is the task of rewriting a text so that it is readable and easily understood. In this paper, we propose a simple yet novel unsupervised sentence simplification system that harnesses parsing structures together with sentence embeddings to produce linguistically effective simplifications. This means our model is capable of introducing substantial modifications to simplify a sentence while maintaining its original semantics and adequate fluency. We establish the unsupervised state-of-the-art at 39.13 SARI on TurkCorpus set and perform competitively against supervised baselines on various quality metrics. Furthermore, we demonstrate our framework's extensibility to other languages via a proof-of-concept on Vietnamese data. Code for reproduction is published at \url{https://github.com/isVy08/USDP}.

Xin Zhou, Weiqing Wang, Wray Buntine et al.

Deep models for Multivariate Time Series (MTS) forecasting have recently demonstrated significant success. Channel-dependent models capture complex dependencies that channel-independent models cannot capture. However, the number of channels in real-world applications outpaces the capabilities of existing channel-dependent models, and contrary to common expectations, some models underperform the channel-independent models in handling high-dimensional data, which raises questions about the performance of channel-dependent models. To address this, our study first investigates the reasons behind the suboptimal performance of these channel-dependent models on high-dimensional MTS data. Our analysis reveals that two primary issues lie in the introduced noise from unrelated series that increases the difficulty of capturing the crucial inter-channel dependencies, and challenges in training strategies due to high-dimensional data. To address these issues, we propose STHD, the Scalable Transformer for High-Dimensional Multivariate Time Series Forecasting. STHD has three components: a) Relation Matrix Sparsity that limits the noise introduced and alleviates the memory issue; b) ReIndex applied as a training strategy to enable a more flexible batch size setting and increase the diversity of training data; and c) Transformer that handles 2-D inputs and captures channel dependencies. These components jointly enable STHD to manage the high-dimensional MTS while maintaining computational feasibility. Furthermore, experimental results show STHD's considerable improvement on three high-dimensional datasets: Crime-Chicago, Wiki-People, and Traffic. The source code and dataset are publicly available https://github.com/xinzzzhou/ScalableTransformer4HighDimensionMTSF.git.

Jionghao Lin, Wei Tan, Ngoc Dang Nguyen et al.

Dialogue acts (DAs) can represent conversational actions of tutors or students that take place during tutoring dialogues. Automating the identification of DAs in tutoring dialogues is significant to the design of dialogue-based intelligent tutoring systems. Many prior studies employ machine learning models to classify DAs in tutoring dialogues and invest much effort to optimize the classification accuracy by using limited amounts of training data (i.e., low-resource data scenario). However, beyond the classification accuracy, the robustness of the classifier is also important, which can reflect the capability of the classifier on learning the patterns from different class distributions. We note that many prior studies on classifying educational DAs employ cross entropy (CE) loss to optimize DA classifiers on low-resource data with imbalanced DA distribution. The DA classifiers in these studies tend to prioritize accuracy on the majority class at the expense of the minority class which might not be robust to the data with imbalanced ratios of different DA classes. To optimize the robustness of classifiers on imbalanced class distributions, we propose to optimize the performance of the DA classifier by maximizing the area under the ROC curve (AUC) score (i.e., AUC maximization). Through extensive experiments, our study provides evidence that (i) by maximizing AUC in the training process, the DA classifier achieves significant performance improvement compared to the CE approach under low-resource data, and (ii) AUC maximization approaches can improve the robustness of the DA classifier under different class imbalance ratios.

Wei Tan, Jionghao Lin, David Lang et al.

Dialogue Acts (DAs) can be used to explain what expert tutors do and what students know during the tutoring process. Most empirical studies adopt the random sampling method to obtain sentence samples for manual annotation of DAs, which are then used to train DA classifiers. However, these studies have paid little attention to sample informativeness, which can reflect the information quantity of the selected samples and inform the extent to which a classifier can learn patterns. Notably, the informativeness level may vary among the samples and the classifier might only need a small amount of low informative samples to learn the patterns. Random sampling may overlook sample informativeness, which consumes human labelling costs and contributes less to training the classifiers. As an alternative, researchers suggest employing statistical sampling methods of Active Learning (AL) to identify the informative samples for training the classifiers. However, the use of AL methods in educational DA classification tasks is under-explored. In this paper, we examine the informativeness of annotated sentence samples. Then, the study investigates how the AL methods can select informative samples to support DA classifiers in the AL sampling process. The results reveal that most annotated sentences present low informativeness in the training dataset and the patterns of these sentences can be easily captured by the DA classifier. We also demonstrate how AL methods can reduce the cost of manual annotation in the AL sampling process.

Xinzhe Li, Ming Liu, Shang Gao et al.

Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work.

Do Huu Dat, Po Yuan Mao, Tien Hoang Nguyen et al.

Compositional Zero-Shot Learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporating compositional thinking into its methodology. Conventional zero-shot learning has difficulty managing unfamiliar combinations of seen and unseen classes because it depends on pre-defined class embeddings. In contrast, Compositional Zero-Shot Learning leverages the inherent hierarchies and structural connections among classes, creating new class representations by combining attributes, components, or other semantic elements. In our paper, we propose a novel framework that for the first time combines the Modern \underline{H}opfield Network with a Mixture \underline{o}f \underline{E}x\underline{p}erts (HOPE) to classify the compositions of previously unseen objects. Specifically, the Modern Hopfield Network creates a memory that stores label prototypes and identifies relevant labels for a given input image. Subsequently, the Mixture of Expert models integrates the image with the appropriate prototype to produce the final composition classification. Our approach achieves SOTA performance on several benchmarks, including MIT-States and UT-Zappos. We also examine how each component contributes to improved generalization.

Ngoc Dang Nguyen, Wei Tan, Wray Buntine et al.

Current work in named entity recognition (NER) uses either cross entropy (CE) or conditional random fields (CRF) as the objective/loss functions to optimize the underlying NER model. Both of these traditional objective functions for the NER problem generally produce adequate performance when the data distribution is balanced and there are sufficient annotated training examples. But since NER is inherently an imbalanced tagging problem, the model performance under the low-resource settings could suffer using these standard objective functions. Based on recent advances in area under the ROC curve (AUC) maximization, we propose to optimize the NER model by maximizing the AUC score. We give evidence that by simply combining two binary-classifiers that maximize the AUC score, significant performance improvement over traditional loss functions is achieved under low-resource NER settings. We also conduct extensive experiments to demonstrate the advantages of our method under the low-resource and highly-imbalanced data distribution settings. To the best of our knowledge, this is the first work that brings AUC maximization to the NER setting. Furthermore, we show that our method is agnostic to different types of NER embeddings, models and domains. The code to replicate this work will be provided upon request.

Ngoc Dang Nguyen, Lan Du, Wray Buntine et al.

Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic characteristics that clinical narratives possess, which leads to unsatisfactory performance. In this paper, we present a simple yet effective hardness-guided domain adaptation (HGDA) framework for bioNER tasks that can effectively leverage the domain hardness information to improve the adaptability of the learnt model in low-resource scenarios. Experimental results on biomedical datasets show that our model can achieve significant performance improvement over the recently published state-of-the-art (SOTA) MetaNER model

Ngoc Phan Phuoc Loc, Toan Huynh La Viet, Thanh Tran Khanh et al.

The rapid growth in submissions to machine learning venues has strained the scientific peer-review system and intensified interest in LLM-based automated peer reviewers. However, how good these systems are actually, especially compared to human reviewers at catching scientific gaps, remains poorly understood. In this work, we introduce PRISM (Peer Review Intelligence via Structured Multi-dimensional assessment), a benchmarking framework that evaluates review quality across four dimensions: Depth of Analysis, Novelty Assessment,Flaw Identification & Major Issues Prioritization, and Multi-dimensional Constructiveness. Unlike most existing evaluations based on surface-level metrics like ROUGE and BLEU, or unconstrained LLM-as-a-judge prompting that conflates fluency with rigor, PRISM grounds each dimension in argument mining, retrieval-augmented verification, and consensus-based scoring. We apply PRISM to benchmark five leading automated reviewer systems and human reviewers on a stratified corpus of reviews from ICLR, ICML, and NeurIPS. The results reveal that LLMs can match or beat human reviewers on individual dimensions: comparable depth of analysis, stronger novelty verification, and highly accurate critique prioritization. However, no single system consistently matches the balanced performance of the human baseline across all dimensions at once. Each exhibits a distinct specialization profile with characteristic blind spots -- failure modes that aggregate metrics miss entirely. The implication is that LLM reviewers are best understood as targeted supplements to human review, effective within specific dimensions, but unreliable as standalone replacements. Our demo and key results can be found at https://khanhthanhdev.github.io/prism-page/.

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

Semi-structured explanation depicts the implicit process of a reasoner with an explicit representation. This explanation highlights how available information in a specific query is utilised and supplemented with information a reasoner produces from its internal weights towards generating an answer. Despite the recent improvements in generative capabilities of language models, producing structured explanations to verify a model's true reasoning capabilities remains a challenge. This issue is particularly pronounced for not-so-large LMs (e.g., FLAN-T5-XXL). In this work, we first underscore the limitations of supervised fine-tuning (SFT) in tackling this challenge, and then introduce a carefully crafted reward engineering method in reinforcement learning (RL) to better address this problem. We investigate multiple reward aggregation methods and provide a detailed discussion which sheds light on the promising potential of RL for future research. Our proposed method on two semi-structured explanation generation benchmarks (ExplaGraph and COPA-SSE) achieves new state-of-the-art results.

Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine et al.

Logical reasoning is a fundamental task in natural language processing that presents significant challenges to Large Language Models (LLMs). The inherent characteristics of logical reasoning makes it well-suited for symbolic representations such as first-order logic (FOL). Research in symbolic logical reasoning explored FOL generation using state-of-the-art LLMs (i.e., GPT-4) to produce FOL translations of natural language (NL) statements, but errors in translation are usually not the focus. We address this by categorizing the translation errors in FOL statements generated by LLMs. To make progress towards improving the quality of FOL translations for smaller language models such as LLaMA-2 13B and Mistral 7B, we create ProofFOL, a high-quality FOL-annotated subset of ProofWriter dataset using GPT-4o. The models fine-tuned on this silver standard data achieve a significant gain in performance when compared to larger language models such as LLaMA-2 70B. In addition to improving the model using large data, we also tackle the issue of data scarcity and introduce an incremental framework encompassing of data augmentation and verification steps. In the augmentation process, a single pair of (premises, conclusion) is split into multiple new instances based on the predicates and FOLs. This data is used for fine-tuning, and the inference on this model generates FOLs with fewer errors over the model trained on the original data. Our investigation on the translation errors leads to generation of a perturbation dataset, which is used to train a verifier that corrects potential syntactic and semantic FOL translation errors. We demonstrate an efficient method for making the most of a limited existing human-annotated dataset. Our results show state-of-the-art performance for ProofWriter and ProntoQA datasets using ProofFOL on LLaMA-2 and Mistral models.

Ngoc Dang Nguyen, Wei Tan, Lan Du et al.

Named entity recognition (NER), a task that identifies and categorizes named entities such as persons or organizations from text, is traditionally framed as a multi-class classification problem. However, this approach often overlooks the issues of imbalanced label distributions, particularly in low-resource settings, which is common in certain NER contexts, like biomedical NER (bioNER). To address these issues, we propose an innovative reformulation of the multi-class problem as a one-vs-all (OVA) learning problem and introduce a loss function based on the area under the receiver operating characteristic curve (AUC). To enhance the efficiency of our OVA-based approach, we propose two training strategies: one groups labels with similar linguistic characteristics, and another employs meta-learning. The superiority of our approach is confirmed by its performance, which surpasses traditional NER learning in varying NER settings.

Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine et al.

The use of formal language for deductive logical reasoning aligns well with language models (LMs), where translating natural language (NL) into first-order logic (FOL) and employing an external solver results in a verifiable and therefore reliable reasoning system. However, smaller LMs often struggle with this translation task, frequently producing incorrect symbolic outputs due to formatting and translation errors. Existing approaches typically rely on self-iteration to correct these errors, but such methods depend heavily on the capabilities of the underlying model. To address this, we first categorize common errors and fine-tune smaller LMs using data synthesized by large language models. The evaluation is performed using the defined error categories. We introduce incremental inference, which divides inference into two stages, predicate generation and FOL translation, providing greater control over model behavior and enhancing generation quality as measured by predicate metrics. This decomposition framework also enables the use of a verification module that targets predicate-arity errors to further improve performance. Our study evaluates three families of models across four logical-reasoning datasets. The comprehensive fine-tuning, incremental inference, and verification modules reduce error rates, increase predicate coverage, and improve reasoning performance for smaller LMs, moving us closer to developing reliable and accessible symbolic-reasoning systems.

Tung X. Nguyen, Nhu Vo, Giang-Son Nguyen et al.

Code-switching (CS), which is when Vietnamese speech uses English words like drug names or procedures, is a common phenomenon in Vietnamese medical communication. This creates challenges for Automatic Speech Recognition (ASR) systems, especially in low-resource languages like Vietnamese. Current most ASR systems struggle to recognize correctly English medical terms within Vietnamese sentences, and no benchmark addresses this challenge. In this paper, we construct a 34-hour \textbf{Vi}etnamese \textbf{Med}ical \textbf{C}ode-\textbf{S}witching \textbf{S}peech dataset (ViMedCSS) containing 16,576 utterances. Each utterance includes at least one English medical term drawn from a curated bilingual lexicon covering five medical topics. Using this dataset, we evaluate several state-of-the-art ASR models and examine different specific fine-tuning strategies for improving medical term recognition to investigate the best approach to solve in the dataset. Experimental results show that Vietnamese-optimized models perform better on general segments, while multilingual pretraining helps capture English insertions. The combination of both approaches yields the best balance between overall and code-switched accuracy. This work provides the first benchmark for Vietnamese medical code-switching and offers insights into effective domain adaptation for low-resource, multilingual ASR systems.

Gia-Bao Dinh Ho, Chang Wei Tan, Zahra Zamanzadeh Darban et al.

Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences. Our work introduces a novel problem setting focusing on these moments as turning points (TPs), accompanied by a meticulously curated, high-consensus, human-annotated multi-modal dataset. We provide precise timestamps, descriptions, and visual-textual evidence high-lighting changes in emotions, behaviors, perspectives, and decisions at these turning points. We also propose a framework, TPMaven, utilizing state-of-the-art vision-language models to construct a narrative from the videos and large language models to classify and detect turning points in our multi-modal dataset. Evaluation results show that TPMaven achieves an F1-score of 0.88 in classification and 0.61 in detection, with additional explanations aligning with human expectations.

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational resources and lacking scalability across diverse reasoning tasks. To address these limitations, we propose VerifiAgent, a unified verification agent that integrates two levels of verification: meta-verification, which assesses completeness and consistency in model responses, and tool-based adaptive verification, where VerifiAgent autonomously selects appropriate verification tools based on the reasoning type, including mathematical, logical, or commonsense reasoning. This adaptive approach ensures both efficiency and robustness across different verification scenarios. Experimental results show that VerifiAgent outperforms baseline verification methods (e.g., deductive verifier, backward verifier) among all reasoning tasks. Additionally, it can further enhance reasoning accuracy by leveraging feedback from verification results. VerifiAgent can also be effectively applied to inference scaling, achieving better results with fewer generated samples and costs compared to existing process reward models in the mathematical reasoning domain. Code is available at https://github.com/Jiuzhouh/VerifiAgent

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

Large language models have demonstrated remarkable capabilities in complex mathematical reasoning tasks, but they inevitably generate errors throughout multi-step solutions. Process-level Reward Models (PRMs) have shown great promise by providing supervision and evaluation at each intermediate step, thereby effectively improving the models' reasoning abilities. However, training effective PRMs requires high-quality process reward data, yet existing methods for constructing such data are often labour-intensive or inefficient. In this paper, we propose an uncertainty-driven framework for automated process reward data construction, encompassing both data generation and annotation processes for PRMs. Additionally, we identify the limitations of both majority vote and PRMs, and introduce two generic uncertainty-aware output aggregation methods: Hybrid Majority Reward Vote and Weighted Reward Frequency Vote, which combine the strengths of majority vote with PRMs. Extensive experiments on ProcessBench, MATH, and GSMPlus show the effectiveness and efficiency of the proposed PRM data construction framework, and demonstrate that the two output aggregation methods further improve the mathematical reasoning abilities across diverse PRMs. The code and data will be publicly available at https://github.com/Jiuzhouh/UnPRM.

Xiaohao Yang, He Zhao, Dinh Phung et al.

Topic modeling has been a widely used tool for unsupervised text analysis. However, comprehensive evaluations of a topic model remain challenging. Existing evaluation methods are either less comparable across different models (e.g., perplexity) or focus on only one specific aspect of a model (e.g., topic quality or document representation quality) at a time, which is insufficient to reflect the overall model performance. In this paper, we propose WALM (Word Agreement with Language Model), a new evaluation method for topic modeling that considers the semantic quality of document representations and topics in a joint manner, leveraging the power of Large Language Models (LLMs). With extensive experiments involving different types of topic models, WALM is shown to align with human judgment and can serve as a complementary evaluation method to the existing ones, bringing a new perspective to topic modeling. Our software package is available at https://github.com/Xiaohao-Yang/Topic_Model_Evaluation.

Jueqing Lu, Wray Buntine, Yuanyuan Qi et al.

Resolving conflicts is critical for improving the reliability of multi-view classification. While prior work focuses on learning consistent and informative representations across views, it often assumes perfect alignment and equal importance of all views, an assumption rarely met in real-world scenarios, as some views may express distinct information. To address this, we develop a computational trust-based discounting method that enhances the Evidential Multi-view framework by accounting for the instance-wise reliability of each view through a probability-sensitive trust mechanism. We evaluate our method on six real-world datasets using Top-1 Accuracy, Fleiss' Kappa, and a new metric, Multi-View Agreement with Ground Truth, to assess prediction reliability. We also assess the effectiveness of uncertainty in indicating prediction correctness via AUROC. Additionally, we test the scalability of our method through end-to-end training on a large-scale dataset. The experimental results show that computational trust can effectively resolve conflicts, paving the way for more reliable multi-view classification models in real-world applications. Codes available at: https://github.com/OverfitFlow/Trust4Conflict

Islam Nassar, Samitha Herath, Ehsan Abbasnejad et al.

Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they only rely on the model's prediction to make labeling decisions without considering any prior knowledge about the visual similarity among the classes. In this paper, we demonstrate that this degrades the quality of pseudo-labeling as it poorly represents visually similar classes in the pool of pseudo-labeled data. We propose SemCo, a method which leverages label semantics and co-training to address this problem. We train two classifiers with two different views of the class labels: one classifier uses the one-hot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together. We then co-train the two classifiers to learn based on their disagreements. We show that our method achieves state-of-the-art performance across various SSL tasks including 5.6% accuracy improvement on Mini-ImageNet dataset with 1000 labeled examples. We also show that our method requires smaller batch size and fewer training iterations to reach its best performance. We make our code available at https://github.com/islam-nassar/semco.

Theodore Papamarkou, Pierre Alquier, Matthias Bauer et al.

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for LLM inference, this position paper argues that the control layer of an agentic AI system (that orchestrates LLMs and tools) is a clear case where Bayesian principles should shine. Bayesian decision theory provides a framework for agentic systems that can help to maintain beliefs over task-relevant latent quantities, to update these beliefs from observed agentic and human-AI interactions, and to choose actions. Making LLMs themselves explicitly Bayesian belief-updating engines remains computationally intensive and conceptually nontrivial as a general modeling target. In contrast, this paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system, not necessarily the LLM agent parameters. This paper articulates practical properties for Bayesian control that fit modern agentic AI systems and human-AI collaboration, and provides concrete examples and design patterns to illustrate how calibrated beliefs and utility-aware policies can improve agentic AI orchestration.

Wei Tan, Lan Du, Wray Buntine

The effectiveness of active learning largely depends on the sampling efficiency of the acquisition function. Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the reduction in classification error, and more general costs fit in the same framework. We propose Bayesian Estimate of Mean Proper Scores (BEMPS) to estimate the increase in strictly proper scores such as log probability or negative mean square error within this framework. We also prove convergence results for this general class of costs. To facilitate better experimentation with the new acquisition functions, we develop a complementary batch AL algorithm that encourages diversity in the vector of expected changes in scores for unlabeled data. To allow high-performance classifiers, we combine deep ensembles, and dynamic validation set construction on pretrained models, and further speed up the ensemble process with the idea of Monte Carlo Dropout. Extensive experiments on both texts and images show that the use of mean square error and log probability with BEMPS yields robust acquisition functions and well-calibrated classifiers, and consistently outperforms the others tested. The advantages of BEMPS over the others are further supported by a set of qualitative analyses, where we visualise their sampling behaviour using data maps and t-SNE plots.

Nhu Vo, Dat Quoc Nguyen, Dung D. Le et al.

Machine translation for Vietnamese-English in the medical domain is still an under-explored research area. In this paper, we introduce MedEV -- a high-quality Vietnamese-English parallel dataset constructed specifically for the medical domain, comprising approximately 360K sentence pairs. We conduct extensive experiments comparing Google Translate, ChatGPT (gpt-3.5-turbo), state-of-the-art Vietnamese-English neural machine translation models and pre-trained bilingual/multilingual sequence-to-sequence models on our new MedEV dataset. Experimental results show that the best performance is achieved by fine-tuning "vinai-translate" for each translation direction. We publicly release our dataset to promote further research.

Wei Tan, Ngoc Dang Nguyen, Lan Du et al.

Within the scope of natural language processing, the domain of multi-label text classification is uniquely challenging due to its expansive and uneven label distribution. The complexity deepens due to the demand for an extensive set of annotated data for training an advanced deep learning model, especially in specialized fields where the labeling task can be labor-intensive and often requires domain-specific knowledge. Addressing these challenges, our study introduces a novel deep active learning strategy, capitalizing on the Beta family of proper scoring rules within the Expected Loss Reduction framework. It computes the expected increase in scores using the Beta Scoring Rules, which are then transformed into sample vector representations. These vector representations guide the diverse selection of informative samples, directly linking this process to the model's expected proper score. Comprehensive evaluations across both synthetic and real datasets reveal our method's capability to often outperform established acquisition techniques in multi-label text classification, presenting encouraging outcomes across various architectural and dataset scenarios.

Ming Liu, Ran Liu, Ye Zhu et al.

ChatGPT has changed the AI community and an active research line is the performance evaluation of ChatGPT. A key challenge for the evaluation is that ChatGPT is still closed-source and traditional benchmark datasets may have been used by ChatGPT as the training data. In this paper, (i) we survey recent studies which uncover the real performance levels of ChatGPT in seven categories of NLP tasks, (ii) review the social implications and safety issues of ChatGPT, and (iii) emphasize key challenges and opportunities for its evaluation. We hope our survey can shed some light on its blackbox manner, so that researchers are not misleaded by its surface generation.

Xin Zhou, Weiqing Wang, Francisco J. Baldán et al.

While multimodal data sources are increasingly available from real-world forecasting, most existing research remains on unimodal time series. In this work, we present MoTime, a suite of multimodal time series forecasting datasets that pair temporal signals with external modalities such as text, metadata, and images. Covering diverse domains, MoTime supports structured evaluation of modality utility under two scenarios: 1) the common forecasting task, where varying-length history is available, and 2) cold-start forecasting, where no historical data is available. Experiments show that external modalities can improve forecasting performance in both scenarios, with particularly strong benefits for short series in some datasets, though the impact varies depending on data characteristics. By making datasets and findings publicly available, we aim to support more comprehensive and realistic benchmarks in future multimodal time series forecasting research.

Weicong Tan, Weiqing Wang, Xin Zhou et al.

Most existing medication recommendation models learn representations for medical concepts based on electronic health records (EHRs) and make recommendations with learnt representations. However, most medications appear in the dataset for limited times, resulting in insufficient learning of their representations. Medical ontologies are the hierarchical classification systems for medical terms where similar terms are in the same class on a certain level. In this paper, we propose OntoMedRec, the logically-pretrained and model-agnostic medical Ontology Encoders for Medication Recommendation that addresses data sparsity problem with medical ontologies. We conduct comprehensive experiments on benchmark datasets to evaluate the effectiveness of OntoMedRec, and the result shows the integration of OntoMedRec improves the performance of various models in both the entire EHR datasets and the admissions with few-shot medications. We provide the GitHub repository for the source code on https://anonymous.4open.science/r/OntoMedRec-D123

Jueqing Lu, Yuanyuan Qi, Xiaohao Yang et al.

The performance of Visio-Language Transformers drops sharply when an input modality (e.g., image) is missing, because the model is forced to make predictions using incomplete information. Existing missing-aware prompt methods help reduce this degradation, but they still rely on conventional prediction heads (e.g., a Fully-Connected layer) that compute class scores in the same way regardless of which modality is present or absent. We introduce Decoupled Prototype Learning (DPL), a new prediction head architecture that explicitly adjusts its decision process to the observed input modalities. For each class, DPL selects a set of prototypes specific to the current missing-modality cases (image-missing, text-missing, or mixed-missing). Each prototype is then decomposed into image-specific and text-specific components, enabling the head to make decisions that depend on the information actually present. This adaptive design allows DPL to handle inputs with missing modalities more effectively while remaining fully compatible with existing prompt-based frameworks. Extensive experiments on MM-IMDb, UPMC Food-101, and Hateful Memes demonstrate that DPL outperforms state-of-the-art approaches across all widely used multimodal imag-text datasets and various missing cases.

Nhu Vo, Nu-Uyen-Phuong Le, Dung D. Le et al.

Medical English-Vietnamese machine translation (En-Vi MT) is essential for healthcare access and communication in Vietnam, yet Vietnamese remains a low-resource and under-studied language. We systematically evaluate prompting strategies for six multilingual LLMs (0.5B-9B parameters) on the MedEV dataset, comparing zero-shot, few-shot, and dictionary-augmented prompting with Meddict, an English-Vietnamese medical lexicon. Results show that model scale is the primary driver of performance: larger LLMs achieve strong zero-shot results, while few-shot prompting yields only marginal improvements. In contrast, terminology-aware cues and embedding-based example retrieval consistently improve domain-specific translation. These findings underscore both the promise and the current limitations of multilingual LLMs for medical En-Vi MT.

Ramya Keerthy Thatikonda, Wray Buntine, Ehsan Shareghi

Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with dedicated outcome or process reward models has opened up new avenues to enhance LLMs performance in complex reasoning tasks, this space is under-explored in deductive logical reasoning. We present a set of Outcome Reward Models (ORMs) for deductive reasoning. To train the ORMs we mainly generate data using Chain-of-Thought (CoT) with single and multiple samples. Additionally, we propose a novel tactic to further expand the type of errors covered in the training dataset of the ORM. In particular, we propose an echo generation technique that leverages LLMs' tendency to reflect incorrect assumptions made in prompts to extract additional training data, covering previously unexplored error types. While a standard CoT chain may contain errors likely to be made by the reasoner, the echo strategy deliberately steers the model toward incorrect reasoning. We show that ORMs trained on CoT and echo-augmented data demonstrate improved performance on the FOLIO, JustLogic, and ProverQA datasets across four different LLMs.

Chenkai Wu, Yuanyuan Qi, Xiaohao Yang et al.

Deep Active Learning (DAL) reduces annotation costs by selecting the most informative unlabeled samples during training. As real-world applications become more complex, challenges stemming from distribution shifts (e.g., open-set recognition) and data imbalance have gained increasing attention, prompting the development of numerous DAL algorithms. However, the lack of a unified platform has hindered fair and systematic evaluation under diverse conditions. Therefore, we present a new DAL platform ALScope for classification tasks, integrating 10 datasets from computer vision (CV) and natural language processing (NLP), and 21 representative DAL algorithms, including both classical baselines and recent approaches designed to handle challenges such as distribution shifts and data imbalance. This platform supports flexible configuration of key experimental factors, ranging from algorithm and dataset choices to task-specific factors like out-of-distribution (OOD) sample ratio, and class imbalance ratio, enabling comprehensive and realistic evaluation. We conduct extensive experiments on this platform under various settings. Our findings show that: (1) DAL algorithms' performance varies significantly across domains and task settings; (2) in non-standard scenarios such as imbalanced and open-set settings, DAL algorithms show room for improvement and require further investigation; and (3) some algorithms achieve good performance, but require significantly longer selection time.

Ramya Keerthy Thatikonda, Wray Buntine, Ehsan Shareghi

The recent successful paradigm of solving logical reasoning problems with tool-augmented large language models (LLMs) leverages translation of natural language (NL) statements into First-Order Logic~(FOL) and external theorem provers. However, the correctness of FOL statements, comprising operators and text, often go unverified due to the lack of a reliable evaluation metric for comparing generated and ground-truth FOLs. In this paper, we conduct a comprehensive study on the sensitivity of existing NL-, FOL-, and graph-based metrics to capture differences between a sampled FOL and its corresponding ground-truth. We then measure the alignment between a metric-based ranking of FOL outputs and a strong LLM as-a-judge. To do this, we first apply operator and text-based perturbations to ground-truth FOL statements to assess metric sensitivity. We then evaluate metric robustness by comparing the metrics against LLMs judgment. Our empirical findings highlight a clear oversensitivity in the n-gram metric BLEU for text perturbations. The operator perturbation affects the semantic graph metric Smatch++ for structural changes, and the FOL metric for specific operator changes. We observe a closer alignment between BertScore and LLM judgement, proving the importance of semantic evaluation. Additionally, we show that combining metrics enhances both robustness and sensitivity compared to using individual metrics.

Do Huu Dat, Do Duc Anh, Anh Tuan Luu et al.

While diffusion models excel at conditional generating high-quality images, prior works in discrete diffusion models were not evaluated on conditional long-text generation. In this work, we address the limitations of prior discrete diffusion models for conditional long-text generation, particularly in long sequence-to-sequence tasks such as abstractive summarization. Despite fast decoding speeds compared to autoregressive methods, previous diffusion models failed on the abstractive summarization task due to the incompatibility between the backbone architectures and the random noising process. To overcome these challenges, we introduce a novel semantic-aware noising process that enables Transformer backbones to handle long sequences effectively. Additionally, we propose CrossMamba, an adaptation of the Mamba model to the encoder-decoder paradigm, which integrates seamlessly with the random absorbing noising process. Our approaches achieve state-of-the-art performance on three benchmark summarization datasets: Gigaword, CNN/DailyMail, and Arxiv, outperforming existing discrete diffusion models on ROUGE metrics as well as possessing much faster speed in inference compared to autoregressive models.

Jiuzhou Han, Wray Buntine, Ehsan Shareghi

While Language Agents have achieved promising success by placing Large Language Models at the core of a more versatile design that dynamically interacts with the external world, the existing approaches neglect the notion of uncertainty during these interactions. We present the Uncertainty-Aware Language Agent (UALA), a framework that orchestrates the interaction between the agent and the external world using uncertainty quantification. Compared with other well-known counterparts like ReAct, our extensive experiments across 3 representative tasks (HotpotQA, StrategyQA, MMLU) and various LLM sizes demonstrate that UALA brings a significant improvement of performance, while having a substantially lower reliance on the external world (i.e., reduced number of tool calls and tokens). Our analyses provide various insights including the great potential of UALA compared with agent fine-tuning, and underscore the unreliability of verbalised confidence of LLMs as a proxy for uncertainty.

Jiuzhou Han, Nigel Collier, Wray Buntine et al.

Large language models (LLMs) have shown great abilities of solving various natural language tasks in different domains. Due to the training objective of LLMs and their pre-training data, LLMs are not very well equipped for tasks involving structured data generation. We propose a framework, Prompting with Iterative Verification (PiVe), to improve graph-based generative capability of LLMs. We show how a small language model could be trained to act as a verifier module for the output of an LLM~(i.e., ChatGPT, GPT-4), and to iteratively improve its performance via fine-grained corrective instructions. We also show how the verifier module could apply iterative corrections offline for a more cost-effective solution to the text-to-graph generation task. Experiments on three graph-based datasets show consistent improvement gained via PiVe. Additionally, we create GenWiki-HIQ and highlight that the verifier module can be used as a data augmentation tool to help improve the quality of automatically generated parallel text-graph datasets.

Wei Tan, Lan Du, Wray Buntine

We study acquisition functions for active learning (AL) for text classification. The Expected Loss Reduction (ELR) method focuses on a Bayesian estimate of the reduction in classification error, recently updated with Mean Objective Cost of Uncertainty (MOCU). We convert the ELR framework to estimate the increase in (strictly proper) scores like log probability or negative mean square error, which we call Bayesian Estimate of Mean Proper Scores (BEMPS). We also prove convergence results borrowing techniques used with MOCU. In order to allow better experimentation with the new acquisition functions, we develop a complementary batch AL algorithm, which encourages diversity in the vector of expected changes in scores for unlabelled data. To allow high performance text classifiers, we combine ensembling and dynamic validation set construction on pretrained language models. Extensive experimental evaluation then explores how these different acquisition functions perform. The results show that the use of mean square error and log probability with BEMPS yields robust acquisition functions, which consistently outperform the others tested.

Fahimeh Saleh, Wray Buntine, Gholamreza Haffari et al.

Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translation by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. HKD generates a set of multilingual teacher-assistant models via a selective knowledge distillation mechanism based on the language groups, and then distils the ultimate multilingual model from those assistants in an adaptive way. Experimental results derived from the TED dataset with 53 languages demonstrate the effectiveness of our approach in avoiding the negative transfer effect in MNMT, leading to an improved translation performance (about 1 BLEU score on average) compared to strong baselines.

Lan Zhang, Wray Buntine, Ehsan Shareghi

Deep generative models have been widely used in several areas of NLP, and various techniques have been proposed to augment them or address their training challenges. In this paper, we propose a simple modification to Variational Autoencoders (VAEs) by using an Isotropic Gaussian Posterior (IGP) that allows for better utilisation of their latent representation space. This model avoids the sub-optimal behavior of VAEs related to inactive dimensions in the representation space. We provide both theoretical analysis, and empirical evidence on various datasets and tasks that show IGP leads to consistent improvement on several quantitative and qualitative grounds, from downstream task performance and sample efficiency to robustness. Additionally, we give insights about the representational properties encouraged by IGP and also show that its gain generalises to image domain as well.

Yuan Jin, He Zhao, Ming Liu et al.

Neural topic models (NTMs) apply deep neural networks to topic modelling. Despite their success, NTMs generally ignore two important aspects: (1) only document-level word count information is utilized for the training, while more fine-grained sentence-level information is ignored, and (2) external semantic knowledge regarding documents, sentences and words are not exploited for the training. To address these issues, we propose a variational autoencoder (VAE) NTM model that jointly reconstructs the sentence and document word counts using combinations of bag-of-words (BoW) topical embeddings and pre-trained semantic embeddings. The pre-trained embeddings are first transformed into a common latent topical space to align their semantics with the BoW embeddings. Our model also features hierarchical KL divergence to leverage embeddings of each document to regularize those of their sentences, thereby paying more attention to semantically relevant sentences. Both quantitative and qualitative experiments have shown the efficacy of our model in 1) lowering the reconstruction errors at both the sentence and document levels, and 2) discovering more coherent topics from real-world datasets.

Kelvin Lo, Yuan Jin, Weicong Tan et al.

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level transformer-based segmentation model based on the sentence embeddings. The bottom-level component transfers the pre-trained knowledge learned from large external corpora under both single and pair-wise supervised NLP tasks to model the sentence embeddings for the documents. Given the sentence embeddings, the upper-level transformer is trained to recover the segmentation boundaries as well as the topic labels of each sentence. Equipped with a multi-task loss and the pre-trained knowledge, Transformer$^2$ can better capture the semantic coherence within the same segments. Our experiments show that (1) Transformer$^2$ manages to surpass state-of-the-art text segmentation models in terms of a commonly-used semantic coherence measure; (2) in most cases, both single and pair-wise pre-trained knowledge contribute to the model performance; (3) bottom-level sentence encoders pre-trained on specific languages yield better performance than those pre-trained on specific domains.

He Zhao, Dinh Phung, Viet Huynh et al.

Topic modelling has been a successful technique for text analysis for almost twenty years. When topic modelling met deep neural networks, there emerged a new and increasingly popular research area, neural topic models, with over a hundred models developed and a wide range of applications in neural language understanding such as text generation, summarisation and language models. There is a need to summarise research developments and discuss open problems and future directions. In this paper, we provide a focused yet comprehensive overview of neural topic models for interested researchers in the AI community, so as to facilitate them to navigate and innovate in this fast-growing research area. To the best of our knowledge, ours is the first review focusing on this specific topic.

Dilini Rajapaksha, Chakkrit Tantithamthavorn, Jirayus Jiarpakdee et al.

Software Quality Assurance (SQA) planning aims to define proactive plans, such as defining maximum file size, to prevent the occurrence of software defects in future releases. To aid this, defect prediction models have been proposed to generate insights as the most important factors that are associated with software quality. Such insights that are derived from traditional defect models are far from actionable-i.e., practitioners still do not know what they should do or avoid to decrease the risk of having defects, and what is the risk threshold for each metric. A lack of actionable guidance and risk threshold can lead to inefficient and ineffective SQA planning processes. In this paper, we investigate the practitioners' perceptions of current SQA planning activities, current challenges of such SQA planning activities, and propose four types of guidance to support SQA planning. We then propose and evaluate our AI-Driven SQAPlanner approach, a novel approach for generating four types of guidance and their associated risk thresholds in the form of rule-based explanations for the predictions of defect prediction models. Finally, we develop and evaluate an information visualization for our SQAPlanner approach. Through the use of qualitative survey and empirical evaluation, our results lead us to conclude that SQAPlanner is needed, effective, stable, and practically applicable. We also find that 80% of our survey respondents perceived that our visualization is more actionable. Thus, our SQAPlanner paves a way for novel research in actionable software analytics-i.e., generating actionable guidance on what should practitioners do and not do to decrease the risk of having defects to support SQA planning.

Bhagya Hettige, Weiqing Wang, Yuan-Fang Li et al.

Predicting (1) when the next hospital admission occurs and (2) what will happen in the next admission about a patient by mining electronic health record (EHR) data can provide granular readmission predictions to assist clinical decision making. Recurrent neural network (RNN) and point process models are usually employed in modelling temporal sequential data. Simple RNN models assume that sequences of hospital visits follow strict causal dependencies between consecutive visits. However, in the real-world, a patient may have multiple co-existing chronic medical conditions, i.e., multimorbidity, which results in a cascade of visits where a non-immediate historical visit can be most influential to the next visit. Although a point process (e.g., Hawkes process) is able to model a cascade temporal relationship, it strongly relies on a prior generative process assumption. We propose a novel model, MEDCAS, to address these challenges. MEDCAS combines the strengths of RNN-based models and point processes by integrating point processes in modelling visit types and time gaps into an attention-based sequence-to-sequence learning model, which is able to capture the temporal cascade relationships. To supplement the patients with short visit sequences, a structural modelling technique with graph-based methods is used to construct the markers of the point process in MEDCAS. Extensive experiments on three real-world EHR datasets have been performed and the results demonstrate that \texttt{MEDCAS} outperforms state-of-the-art models in both tasks.

Yuan Jin, Wray Buntine, Francois Petitjean et al.

Supervised learning, characterized by both discriminative and generative learning, seeks to predict the values of single (or sometimes multiple) predefined target attributes based on a predefined set of predictor attributes. For applications where the information available and predictions to be made may vary from instance to instance, we propose the task of target-agnostic learning where arbitrary disjoint sets of attributes can be used for each of predictors and targets for each to-be-predicted instance. For this task, we survey a wide range of techniques available for handling missing values, self-supervised training and pseudo-likelihood training, and adapt them to a suite of algorithms that are suitable for the task. We conduct extensive experiments on this suite of algorithms on a large collection of categorical, continuous and discretized datasets, and report their performance in terms of both classification and regression errors. We also report the training and prediction time of these algorithms when handling large-scale datasets. Both generative and self-supervised learning models are shown to perform well at the task, although their characteristics towards the different types of data are quite different. Nevertheless, our derived theorem for the pseudo-likelihood theory also shows that they are related for inferring a joint distribution model based on the pseudo-likelihood training.

Fahimeh Saleh, Wray Buntine, Gholamreza Haffari

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model trained on a high-resource language-pair and fine-tuning it on the data of the low-resource MT condition of interest. However, it is not clear generally which high-resource language-pair offers the best transfer learning for the target MT setting. Furthermore, different transferred models may have complementary semantic and/or syntactic strengths, hence using only one model may be sub-optimal. In this paper, we tackle this problem using knowledge distillation, where we propose to distill the knowledge of ensemble of teacher models to a single student model. As the quality of these teacher models varies, we propose an effective adaptive knowledge distillation approach to dynamically adjust the contribution of the teacher models during the distillation process. Experiments on transferring from a collection of six language pairs from IWSLT to five low-resource language-pairs from TED Talks demonstrate the effectiveness of our approach, achieving up to +0.9 BLEU score improvement compared to strong baselines.

He Zhao, Dinh Phung, Viet Huynh et al.

Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis. However, it is usually hard for existing NTMs to achieve good document representation and coherent/diverse topics at the same time. Moreover, they often degrade their performance severely on short documents. The requirement of reparameterisation could also comprise their training quality and model flexibility. To address these shortcomings, we present a new neural topic model via the theory of optimal transport (OT). Specifically, we propose to learn the topic distribution of a document by directly minimising its OT distance to the document's word distributions. Importantly, the cost matrix of the OT distance models the weights between topics and words, which is constructed by the distances between topics and words in an embedding space. Our proposed model can be trained efficiently with a differentiable loss. Extensive experiments show that our framework significantly outperforms the state-of-the-art NTMs on discovering more coherent and diverse topics and deriving better document representations for both regular and short texts.

Laurent Valentin Jospin, Wray Buntine, Farid Boussaid et al.

Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems. However, since deep learning methods operate as black boxes, the uncertainty associated with their predictions is often challenging to quantify. Bayesian statistics offer a formalism to understand and quantify the uncertainty associated with deep neural network predictions. This tutorial provides an overview of the relevant literature and a complete toolset to design, implement, train, use and evaluate Bayesian Neural Networks, i.e. Stochastic Artificial Neural Networks trained using Bayesian methods.

Bhagya Hettige, Yuan-Fang Li, Weiqing Wang et al.

Electronic medical record (EMR) data contains historical sequences of visits of patients, and each visit contains rich information, such as patient demographics, hospital utilisation and medical codes, including diagnosis, procedure and medication codes. Most existing EMR embedding methods capture visit-code associations by constructing input visit representations as binary vectors with a static vocabulary of medical codes. With this limited representation, they fail in encapsulating rich attribute information of visits (demographics and utilisation information) and/or codes (e.g., medical code descriptions). Furthermore, current work considers visits of the same patient as discrete-time events and ignores time gaps between them. However, the time gaps between visits depict dynamics of the patient's medical history inducing varying influences on future visits. To address these limitations, we present $\mathtt{MedGraph}$, a supervised EMR embedding method that captures two types of information: (1) the visit-code associations in an attributed bipartite graph, and (2) the temporal sequencing of visits through a point process. $\mathtt{MedGraph}$ produces Gaussian embeddings for visits and codes to model the uncertainty. We evaluate the performance of $\mathtt{MedGraph}$ through an extensive experimental study and show that $\mathtt{MedGraph}$ outperforms state-of-the-art EMR embedding methods in several medical risk prediction tasks.

Bhagya Hettige, Yuan-Fang Li, Weiqing Wang et al.

Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors in a low-dimensional embedding space, ignoring the uncertainty present in the real-world graphs. Furthermore, many real-world graphs are large-scale and rich in content (e.g. node attributes). In this work, we propose GLACE, a novel, scalable graph embedding method that preserves both graph structure and node attributes effectively and efficiently in an end-to-end manner. GLACE effectively models uncertainty through Gaussian embeddings, and supports inductive inference of new nodes based on their attributes. In our comprehensive experiments, we evaluate GLACE on real-world graphs, and the results demonstrate that GLACE significantly outperforms state-of-the-art embedding methods on multiple graph analysis tasks.