18 citations · 41 across the 38 of their papers we have counts for
39 papers
Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3
Giang Son Nguyen, Nhi Ngoc-Yen Nguyen, Wray Buntine +1
Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found in one language context plays t…
Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs
Ramya Keerthy Thatikonda, Wray Buntine, Ehsan Shareghi
Logical reasoning with large language models (LLMs) is a critical capability, as it reflects a system's ability to correctly deduce hypotheses from a given context using faithful d…
En-ViMedNER: An English-Vietnamese Parallel Biomedical Corpus with UMLS Semantic Type Annotations
Nhu Vo, Phuong Nguyen, Nu Uyen Phuong Le +4
Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information extraction. While corpora with U…
Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
Tung X. Nguyen, Hieu Minh Truong, Giang Son Nguyen +3
Code-switching (CS), the alternation between multiple languages within a single utterance, remains challenging for Automatic Speech Recognition (ASR). To address this issue, we pro…
PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation
Giang Son Nguyen, Tung X. Nguyen, Hieu Minh Truong +3
Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic catego…
Position: agentic AI orchestration should be Bayes-consistent
Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27
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 co…
PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers
Ngoc Phan Phuoc Loc, Toan Huynh La Viet, Thanh Tran Khanh +8
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, h…
ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark
Tung X. Nguyen, Nhu Vo, Giang-Son Nguyen +6
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 chal…
Improving Symbolic Translation of Language Models for Logical Reasoning
Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine +1
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 employin…
Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation
Nhu Vo, Nu-Uyen-Phuong Le, Dung D. Le +2
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 l…
Logical Reasoning with Outcome Reward Models for Test-Time Scaling
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 premi…
ALScope: A Unified Toolkit for Deep Active Learning
Chenkai Wu, Yuanyuan Qi, Xiaohao Yang +4
Deep Active Learning (DAL) reduces annotation costs by selecting the most informative unlabeled samples during training. As real-world applications become more complex, challenges…
Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning
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. Proces…
MoTime: A Dataset Suite for Multimodal Time Series Forecasting
Xin Zhou, Weiqing Wang, Francisco J. Baldán +2
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 sui…
DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities
Jueqing Lu, Yuanyuan Qi, Xiaohao Yang +8
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 infor…
VerifiAgent: a Unified Verification Agent in Language Model Reasoning
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…
Assessing the Sensitivity and Alignment of FOL Closeness Metrics
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…
Strategies for Improving NL-to-FOL Translation with LLMs: Data Generation, Incremental Fine-Tuning, and Verification
Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine +1
Logical reasoning is a fundamental task in natural language processing that presents significant challenges to Large Language Models (LLMs). The inherent characteristics of logical…
MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations
Gia-Bao Dinh Ho, Chang Wei Tan, Zahra Zamanzadeh Darban +3
Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences.…
Scalable Transformer for High Dimensional Multivariate Time Series Forecasting
Xin Zhou, Weiqing Wang, Wray Buntine +4
Deep models for Multivariate Time Series (MTS) forecasting have recently demonstrated significant success. Channel-dependent models capture complex dependencies that channel-indepe…
Discrete Diffusion Language Model for Efficient Text Summarization
Do Huu Dat, Do Duc Anh, Anh Tuan Luu +1
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…
LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models
Xiaohao Yang, He Zhao, Dinh Phung +2
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 e…
Navigating Conflicting Views: Harnessing Trust for Learning
Jueqing Lu, Wray Buntine, Yuanyuan Qi +3
Resolving conflicts is critical for improving the reliability of multi-view classification. While prior work focuses on learning consistent and informative representations across v…
A Survey on the Real Power of ChatGPT
Ming Liu, Ran Liu, Ye Zhu +5
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…