arXiv subjects

Wray Buntine

Publications and source records attributed to Wray Buntine.

At least 19 recordsLinked to original sources

arXiv2026

Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3

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 the same causal role when processing prompts in another language. We study this question using translation-initiation features (Wu et al., 2026). We reproduce the SAE feature discovery method from Wu et al. in Gemma 2 and extend it to multilingual settings that vary prompt language, source language, and target language. We then test whether features that recur across settings affect translation behavior by amplifying or ablating their activations during inference. We also examine whether the method can be applied to Gemma 3. In both models, we observe an identical finding: although we can find more than 20 features that activate frequently across all discovery settings, causal validation shows that nearly all have small or inconsistent effects. In contrast, one feature -- Gemma 2's (L10, 5717) and Gemma 3's (L20, 2456) -- consistently improves COMET scores when amplified and degrades them when ablated across 23 language settings. These results show that feature recurrence can overstate cross-lingual transfer, while identifying a language-agnostic translation-initiation direction in Gemma 2 and Gemma 3.

cs.CL↗

arXiv2026

Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs

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 deductive processes. However, LLM reasoning has often been shown to be sensitive to small surface-level variations in problem formulation, raising questions about whether models truly follow the underlying logical structure. Studying this behavior is challenging because the symbolic components of logical problems, such as operators and predicates, are difficult to systematically manipulate in natural language. We introduce a tool-driven framework for generating controlled, label-preserving edits to logical reasoning problems. Our method operates on symbolic representations of first-order logic and constraint satisfaction problem tasks, enabling targeted modifications to logical operators and other structural components before translating them back into natural language. Using this framework, we evaluate various LLMs under cumulative and individual operator edits and analyze their behavior in response to these changes. Our quantitative and qualitative analyses show that LLM reasoning behavior under controlled operator edits is inconsistent, regardless of model size or family: models sometimes adapt correctly to structural changes but often fail to track their logical consequences. The results from this automated stress test enable an evaluation of language models across different dimensions and help measure the reliability of their reasoning.

cs.CL↗

arXiv2026

En-ViMedNER: An English-Vietnamese Parallel Biomedical Corpus with UMLS Semantic Type Annotations

Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information extraction. While corpora with Unified Medical Language System (UMLS) annotations, such as MedMentions, have driven progress in English biomedical NER, no comparable resource exists for Vietnamese. This paper presents En-ViMedNER, the first English-Vietnamese parallel biomedical NER corpus annotated with UMLS semantic types, which are language-neutral codes providing a shared cross-lingual label space and ensuring direct comparability with existing UMLS-based resources. The corpus contains 4,392 PubMed abstract pairs, 44,892 English-Vietnamese sentence pairs, and 202,949 aligned entity-mention pairs across 21 semantic types adapted from the MedMentions ST21pv dataset. To balance quality and scalability, we have constructed the corpus through automatic translation, expert post-editing, LLM-assisted label projection, and human verification and adjudication. We characterize En-ViMedNER as a large-scale silver-standard corpus with a human-audited and consensus-corrected mini-test subset. We evaluate En-ViMedNER in two settings: (i) Vietnamese-input/Vietnamese-output biomedical NER and (ii) English-input/Vietnamese-output cross-lingual NER. For Vietnamese NER, we benchmark Vietnamese-supervised encoder models, English-supervised multilingual encoder models, and prompt-based LLMs. The best model achieves an F1 score of 52.70 on the test set and 53.78 on the mini-test set. For cross-lingual NER, we benchmark encoder-decoder models and prompt-based LLMs. The best model achieves an F1 score of 45.44 on the mini-test set. We publicly release our corpus, corpus construction pipeline, and baseline models to facilitate future Vietnamese biomedical NLP research.

cs.CL↗

arXiv2026

PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation

Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic categorization of ASR errors for Vietnamese ST, classifying substitution errors by phonetic cause and quantifying their impact on downstream Neural Machine Translation (NMT) performance using Linear Mixed-Effects Modelling. We confirm that most ASR substitution errors arise from phonetic confusions rather than random noise, and that these phonetic errors significantly degrade ST quality. Motivated by this finding, we propose Phonetically-Informed Data Augmentation (PiDA), which generates ASR-like corruptions by substituting words with phonetically similar alternatives using phonetic word embeddings. Fine-tuning on a PiDA-augmented version of FLEURS Vietnamese-English improves translation of erroneous ASR outputs (up to +2.04 BLEU over standard fine-tuning) while also slightly improving clean-text performance.

cs.CL↗

arXiv2026

Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition

Code-switching (CS), the alternation between multiple languages within a single utterance, remains challenging for Automatic Speech Recognition (ASR). To address this issue, we propose a Point-of-Interest (POI)-aware contrastive training framework that improves recognition at CS-critical regions. We first identify CS spans by adopting POI detection method from literature, then construct acoustically plausible near-miss hypotheses by perturbing POIs in ASR N-best outputs and expanding candidates with a large language model. Hard but plausible negatives are retained through filtering with acoustic, phonemic, and textual constraints. Finally, we fine-tune Whisper-small with LoRA using a POI-weighted cross-entropy anchor objective together with a multi-negative contrastive ranking loss. Experiments on CS-FLEURS (cmn-eng) and ViMedCSS (vie-eng) show consistent reductions of over 2% in both general and CS-aware error rates compared to standard LoRA fine-tuning.

cs.CL↗

arXiv2026

PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers

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/.

cs.CL↗

arXiv2026

Position: agentic AI orchestration should be Bayes-consistent

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.

cs.AI↗

arXiv2026

ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark

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 Vietnamese Medical Code-Switching Speech 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.

cs.CL↗

arXiv2026

Improving Symbolic Translation of Language Models for Logical Reasoning

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.

cs.CL↗

arXiv2025

DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities

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.

cs.LG↗

arXiv2025

Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation

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.

cs.CL↗

arXiv2025

Assessing the Sensitivity and Alignment of FOL Closeness Metrics

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.

cs.CL↗

arXiv2025

Logical Reasoning with Outcome Reward Models for Test-Time Scaling

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.

cs.CL↗

arXiv2025

VerifiAgent: a Unified Verification Agent in Language Model Reasoning

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

cs.CL↗

arXiv2025

ALScope: A Unified Toolkit for Deep Active Learning

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.

cs.LG↗

arXiv2025

Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning

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.

cs.AI↗

arXiv2025

Navigating Conflicting Views: Harnessing Trust for Learning

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

cs.LG↗

arXiv2025

MoTime: A Dataset Suite for Multimodal Time Series Forecasting

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.

cs.LG↗