Tianyi Huang

Tianyi Huang, Shenghui Cheng, Stan Z. Li et al.

Clustering aims to group unlabelled samples based on their similarities. It has become a significant tool for the analysis of high-dimensional data. However, most of the clustering methods merely generate pseudo labels and thus are unable to simultaneously present the similarities between different clusters and outliers. This paper proposes a new framework called High-dimensional Clustering onto Hamiltonian Cycle (HCHC) to solve the above problems. First, HCHC combines global structure with local structure in one objective function for deep clustering, improving the labels as relative probabilities, to mine the similarities between different clusters while keeping the local structure in each cluster. Then, the anchors of different clusters are sorted on the optimal Hamiltonian cycle generated by the cluster similarities and mapped on the circumference of a circle. Finally, a sample with a higher probability of a cluster will be mapped closer to the corresponding anchor. In this way, our framework allows us to appreciate three aspects visually and simultaneously - clusters (formed by samples with high probabilities), cluster similarities (represented as circular distances), and outliers (recognized as dots far away from all clusters). The experiments illustrate the superiority of HCHC.

Haoming Guo, Tianyi Huang, Huixuan Huang et al.

The sharing of fake news and conspiracy theories on social media has wide-spread negative effects. By designing and applying different machine learning models, researchers have made progress in detecting fake news from text. However, existing research places a heavy emphasis on general, common-sense fake news, while in reality fake news often involves rapidly changing topics and domain-specific vocabulary. In this paper, we present our methods and results for three fake news detection tasks at MediaEval benchmark 2021 that specifically involve COVID-19 related topics. We experiment with a group of text-based models including Support Vector Machines, Random Forest, BERT, and RoBERTa. We find that a pre-trained transformer yields the best validation results, but a randomly initialized transformer with smart design can also be trained to reach accuracies close to that of the pre-trained transformer.

Zixi Shao, Tao Wang, Yibei Xiao et al.

Designing therapeutic messenger RNA (mRNA) requires creating full-length transcripts that carefully balance stability, translation efficiency, and immune safety. To address this challenge, we propose ProMORNA, a multi-objective generation framework that produces complete mRNA transcripts \textit{de novo} directly from a target protein sequence. Our approach begins by training a BART-style encoder-decoder model on over 6 million natural protein-mRNA pairs. We then introduce Multi-Objective Group Relative Policy Optimization (MO-GRPO) to simultaneously optimize for various biological objectives in a unified way. As a case study, we evaluated ProMORNA on the widely used firefly luciferase target, excluding it from both our supervised training data and the prompt pool. The results indicate that ProMORNA improves the \textit{in silico} Pareto frontier for predicted half-life and translation efficiency relative to standard supervised baselines. Additionally, it achieves higher predicted functional scores than a state-of-the-art baseline under the same evaluation pipeline. These computational findings demonstrate the feasibility of using multi-objective reinforcement learning for full-length mRNA design on unseen targets.

Tianyi Huang, Caden Yang, Emily Yin et al.

Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We present PAVE (Premise-Grounded Answer Validation and Editing), an inference-time validation layer for evidence-grounded question answering. PAVE decomposes retrieved context into question-conditioned atomic facts, drafts an answer, scores how well that draft is supported by the extracted premises, and revises low-support outputs before finalization. The resulting trace makes answer commitment auditable at the level of explicit premises, support scores, and revision decisions. In controlled ablations with a fixed retriever and backbone, PAVE outperforms simpler post-retrieval baselines in two evidence-grounded QA settings, with the largest gain reaching 32.7 accuracy points on a span-grounded benchmark. We view these findings as proof-of-concept evidence that explicit premise extraction plus support-gated revision can strengthen evidence-grounded consistency in retrieval-augmented LLM systems.

Tianyi Huang, Samuel Xu, Jason Tansong Dang et al.

Agentic systems often fail not by being entirely wrong, but by being too precise: a response may be generally useful while particular claims exceed what the evidence supports. We study this failure mode as overcommitment control and introduce compositional selective specificity (CSS), a post-generation layer that decomposes an answer into claims, proposes coarser backoffs, and emits each claim at the most specific calibrated level that appears admissible. The method is designed to express uncertainty as a local semantic backoff rather than as a whole-answer refusal. Across a full LongFact run and HotpotQA pilots, calibrated CSS improves the risk-utility trade-off of fixed drafts. On the full LongFact run, it raises overcommitment-aware utility from 0.846 to 0.913 relative to the no-CSS output while achieving 0.938 specificity retention. These results suggest that claim-level specificity control is a useful uncertainty interface for agentic systems and a target for future distribution-free validity layers.

Tianyi Huang, Nathan Huang, Justin Tang et al.

Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We study one such source of instability: candidate-order sensitivity in listwise factuality evaluation, where several answers can look similarly polished while differing sharply in hallucination risk. We introduce PCFJudge, an inference-time method that reruns the same factuality-first listwise prompt over multiple orderings of the same candidate set and aggregates the resulting scores, ranks, and uncertainty signals into a single consensus decision. On RewardBench 2 Factuality, PCFJudge improves over direct judging by up to 7 absolute points. Development ablations show that the dominant gain comes from permutation consensus itself rather than from heavier arbitration layers. These results suggest that a meaningful share of factuality-judging error arises from order instability, and that averaging over this nuisance variation is a simple and effective way to make LLM evaluation more reliable.

Tianyi Huang, Jingyuan Yi, Peiyang Yu et al.

The proliferation of misinformation on social media has raised significant societal concerns, necessitating robust detection mechanisms. Large Language Models such as GPT-4 and LLaMA2 have been envisioned as possible tools for detecting misinformation based on their advanced natural language understanding and reasoning capabilities. This paper conducts a comparison of LLM-based approaches to detecting misinformation between text-based, multimodal, and agentic approaches. We evaluate the effectiveness of fine-tuned models, zero-shot learning, and systematic fact-checking mechanisms in detecting misinformation across different topic domains like public health, politics, and finance. We also discuss scalability, generalizability, and explainability of the models and recognize key challenges such as hallucination, adversarial attacks on misinformation, and computational resources. Our findings point towards the importance of hybrid approaches that pair structured verification protocols with adaptive learning techniques to enhance detection accuracy and explainability. The paper closes by suggesting potential avenues of future work, including real-time tracking of misinformation, federated learning, and cross-platform detection models.

Tianyi Huang, Ying Kai Deng

In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight inference-time repair layer for retrieval-grounded question answering. CounterRefine first produces a short answer from retrieved evidence, then gathers additional support and conflicting evidence with follow-up queries conditioned on that draft answer, and finally applies a restricted refinement step that outputs either KEEP or REVISE, with proposed revisions accepted only if they pass deterministic validation. In effect, CounterRefine turns retrieval into a mechanism for testing a provisional answer rather than merely collecting more context. On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points. These findings suggest a simple but important direction for knowledgeable foundation models: beyond accessing evidence, they should also be able to use that evidence to reconsider and, when necessary, repair their own answers.

Tianyi Huang, Zeqiu Xu, Peiyang Yu et al.

In this paper, we propose an optimized Transformer model that integrates Bayesian algorithms with a Bidirectional Gated Recurrent Unit (BiGRU), and apply it to fake news classification for the first time. First, we employ the TF-IDF method to extract features from news texts and transform them into numeric representations to facilitate subsequent machine learning tasks. Two sets of experiments are then conducted for fake news detection and classification: one using a Transformer model optimized only with BiGRU, and the other incorporating Bayesian algorithms into the BiGRU-based Transformer. Experimental results show that the BiGRU-optimized Transformer achieves 100% accuracy on the training set and 99.67% on the test set, while the addition of the Bayesian algorithm maintains 100% accuracy on the training set and slightly improves test-set accuracy to 99.73%. This indicates that the Bayesian algorithm boosts model accuracy by 0.06%, further enhancing the detection capability for fake news. Moreover, the proposed algorithm converges rapidly at around the 10th training epoch with accuracy nearing 100%, demonstrating both its effectiveness and its fast classification ability. Overall, the optimized Transformer model, enhanced by the Bayesian algorithm and BiGRU, exhibits excellent continuous learning and detection performance, offering a robust technical means to combat the spread of fake news in the current era of information overload.

Jingyuan Yi, Zeqiu Xu, Tianyi Huang et al.

The pervasiveness of the dissemination of fake news through social media platforms poses critical risks to the trust of the general public, societal stability, and democratic institutions. This challenge calls for novel methodologies in detection, which can keep pace with the dynamic and multi-modal nature of misinformation. Recent works include powering the detection using large language model advances in multimodal frameworks, methodologies using graphs, and adversarial training in the literature of fake news. Based on the different approaches which can bring success, some key highlights will be underlined: enhanced LLM-improves accuracy through more advanced semantics and cross-modality fusion for robust detections. The review further identifies critical gaps in adaptability to dynamic social media trends, real-time, and cross-platform detection capabilities, as well as the ethical challenges thrown up by the misuse of LLMs. Future directions underline the development of style-agnostic models, cross-lingual detection frameworks, and robust policies with a view to mitigating LLM-driven misinformation. This synthesis thus lays a concrete foundation for those researchers and practitioners committed to reinforcing fake news detection systems with complications that keep on growing in the digital landscape.

Jingyuan Yi, Peiyang Yu, Tianyi Huang et al.

Aiming at the latest particle swarm optimization algorithm, this paper proposes an improved Transformer model to improve the accuracy of heart disease prediction and provide a new algorithm idea. We first use three mainstream machine learning classification algorithms - decision tree, random forest and XGBoost, and then output the confusion matrix of these three models. The results showed that the random forest model had the best performance in predicting the classification of heart disease, with an accuracy of 92.2%. Then, we apply the Transformer model based on particle swarm optimization (PSO) algorithm to the same dataset for classification experiment. The results show that the classification accuracy of the model is as high as 96.5%, 4.3 percentage points higher than that of random forest, which verifies the effectiveness of PSO in optimizing Transformer model. From the above research, we can see that particle swarm optimization significantly improves Transformer performance in heart disease prediction. Improving the ability to predict heart disease is a global priority with benefits for all humankind. Accurate prediction can enhance public health, optimize medical resources, and reduce healthcare costs, leading to healthier populations and more productive societies worldwide. This advancement paves the way for more efficient health management and supports the foundation of a healthier, more resilient global community.

Tianyi Huang, Ming Hou, Jiaheng Su et al.

Three-way logical question answering (QA) assigns $True/False/Unknown$ to a hypothesis $H$ given a premise set $S$. While modern large language models (LLMs) can be accurate on isolated examples, we identify two recurring failure modes in 3-way logic QA: (i) negation inconsistency, where answers to $H$ and $\neg H$ violate the deterministic label mapping, and (ii) epistemic $Unknown$, where the model predicts $Unknown$ due to uncertainty or instability even when $S$ entails one side. We present CGD-PD, a lightweight test-time layer that (a) queries a single 3-way classifier on both $H$ and a mechanically negated form of $H$, (b) projects the pair onto a negation-consistent decision when possible, and (c) invokes a proof-driven disambiguation step that uses targeted binary entailment probes to selectively resolve $Unknown$ outcomes, requiring only an average of 4-5 model calls. On the FOLIO benchmark's first-order-logic fields, CGD-PD yields consistent gains across frontier LLMs, with relative improvements in accuracy of up to 16% over the base model, while also reducing $Unknown$ predictions.

Tianyi Huang, Zikun Cui, Cuiqianhe Du et al.

Misleading text detection on social media platforms is a critical research area, as these texts can lead to public misunderstanding, social panic and even economic losses. This paper proposes a novel framework - CL-ISR (Contrastive Learning and Implicit Stance Reasoning), which combines contrastive learning and implicit stance reasoning, to improve the detection accuracy of misleading texts on social media. First, we use the contrastive learning algorithm to improve the model's learning ability of semantic differences between truthful and misleading texts. Contrastive learning could help the model to better capture the distinguishing features between different categories by constructing positive and negative sample pairs. This approach enables the model to capture distinguishing features more effectively, particularly in linguistically complicated situations. Second, we introduce the implicit stance reasoning module, to explore the potential stance tendencies in the text and their relationships with related topics. This method is effective for identifying content that misleads through stance shifting or emotional manipulation, because it can capture the implicit information behind the text. Finally, we integrate these two algorithms together to form a new framework, CL-ISR, which leverages the discriminative power of contrastive learning and the interpretive depth of stance reasoning to significantly improve detection effect.

Tianyi Huang, Elsa Fan

From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a multi-agent framework that systematically identifies biases by disentangling each statement as fact or opinion, assigning a bias intensity score, and providing concise, factual justifications. Evaluated on 1,500 samples from the WikiNPOV dataset, the framework achieves 84.9% accuracy$\unicode{x2014}$an improvement of 13.0% over the zero-shot baseline$\unicode{x2014}$demonstrating the efficacy of explicitly modeling fact versus opinion prior to quantifying bias intensity. By combining enhanced detection accuracy with interpretable explanations, this approach sets a foundation for promoting fairness and accountability in modern language models.

Zikun Cui, Tianyi Huang, Chia-En Chiang et al.

With the proliferation of Large Language Models (LLMs), the detection of misinformation has become increasingly important and complex. This research proposes an innovative verifiable misinformation detection LLM agent that goes beyond traditional true/false binary judgments. The agent actively verifies claims through dynamic interaction with diverse web sources, assesses information source credibility, synthesizes evidence, and provides a complete verifiable reasoning process. Our designed agent architecture includes three core tools: precise web search tool, source credibility assessment tool and numerical claim verification tool. These tools enable the agent to execute multi-step verification strategies, maintain evidence logs, and form comprehensive assessment conclusions. We evaluate using standard misinformation datasets such as FakeNewsNet, comparing with traditional machine learning models and LLMs. Evaluation metrics include standard classification metrics, quality assessment of reasoning processes, and robustness testing against rewritten content. Experimental results show that our agent outperforms baseline methods in misinformation detection accuracy, reasoning transparency, and resistance to information rewriting, providing a new paradigm for trustworthy AI-assisted fact-checking.

Jingyuan Yi, Peiyang Yu, Tianyi Huang et al.

This work proposes an LSTM-based sentiment classification model with multi-head attention mechanism and TF-IDF optimization. Through the integration of TF-IDF feature extraction and multi-head attention, the model significantly improves text sentiment analysis performance. Experimental results on public data sets demonstrate that the new method achieves substantial improvements in the most critical metrics like accuracy, recall, and F1-score compared to baseline models. Specifically, the model achieves an accuracy of 80.28% on the test set, which is improved by about 12% in comparison with standard LSTM models. Ablation experiments also support the necessity and necessity of all modules, in which the impact of multi-head attention is greatest to performance improvement. This research provides a proper approach to sentiment analysis, which can be utilized in public opinion monitoring, product recommendation, etc.

Tianyi Huang

Designing user-centric mobile applications is increasingly essential in educational technology. However, platforms like MIT App Inventor-one of the world's largest educational app development tools-face inherent limitations in supporting modern UI/UX design. This study introduces the Figma-Enhanced App Design (FEAD) Method, a structured framework that integrates Figma's advanced design tools into MIT App Inventor using an identify-design-implement workflow. Leveraging principles such as the 8-point grid system and Gestalt laws of perception, the FEAD Method empowers users to address design gaps, creating visually appealing, functional, and accessible applications. A comparative evaluation revealed that 61.2% of participants perceived FEAD-enhanced designs as on par with professional apps, compared to just 8.2% for baseline designs. These findings highlight the potential of bridging design with development platforms to enhance app creation, offering a scalable framework for students to master both functional and aesthetic design principles and excel in shaping the future of user-centric technology.

Tianyi Huang, Arya Somasundaram

Large Language Models (LLMs) often perpetuate biases in pronoun usage, leading to misrepresentation or exclusion of queer individuals. This paper addresses the specific problem of biased pronoun usage in LLM outputs, particularly the inappropriate use of traditionally gendered pronouns ("he," "she") when inclusive language is needed to accurately represent all identities. We introduce a collaborative agent pipeline designed to mitigate these biases by analyzing and optimizing pronoun usage for inclusivity. Our multi-agent framework includes specialized agents for both bias detection and correction. Experimental evaluations using the Tango dataset-a benchmark focused on gender pronoun usage-demonstrate that our approach significantly improves inclusive pronoun classification, achieving a 32.6 percentage point increase over GPT-4o in correctly disagreeing with inappropriate traditionally gendered pronouns $(χ^2 = 38.57, p < 0.0001)$. These results accentuate the potential of agent-driven frameworks in enhancing fairness and inclusivity in AI-generated content, demonstrating their efficacy in reducing biases and promoting socially responsible AI.

Cuiqianhe Du, Chia-En Chiang, Tianyi Huang et al.

This paper focuses on the detection of potentially dangerous tendencies of social media users in an innovative multimodal way. We integrate Natural Language Processing (NLP) and Graph Neural Networks (GNNs) together. Firstly, we apply NLP on the user-generated text and conduct semantic analysis, sentiment recognition and keyword extraction to get subtle risk signals from social media posts. Meanwhile, we build a heterogeneous user relationship graph based on social interaction and propose a novel relational graph convolutional network to model user relationship, attention relationship and content dissemination path to discover some important structural information and user behaviors. Finally, we combine textual features extracted from these two models above with graph structural information, which provides a more robust and effective way to discover at-risk users. Our experiments on real social media datasets from different platforms show that our model can achieve significant improvement over single-modality methods.

Tianyi Huang

Harmful Algal Blooms (HABs) pose severe threats to aquatic ecosystems and public health, resulting in substantial economic losses globally. Early detection is crucial but often hindered by the scarcity of high-quality datasets necessary for training reliable machine learning (ML) models. This study investigates the use of synthetic data augmentation using Gaussian Copulas to enhance ML-based HAB detection systems. Synthetic datasets of varying sizes (100-1,000 samples) were generated using relevant environmental features$\unicode{x2015}$water temperature, salinity, and UVB radiation$\unicode{x2015}$with corrected Chlorophyll-a concentration as the target variable. Experimental results demonstrate that moderate synthetic augmentation significantly improves model performance (RMSE reduced from 0.4706 to 0.1850; $p < 0.001$). However, excessive synthetic data introduces noise and reduces predictive accuracy, emphasizing the need for a balanced approach to data augmentation. These findings highlight the potential of synthetic data to enhance HAB monitoring systems, offering a scalable and cost-effective method for early detection and mitigation of ecological and public health risks.

Tianyi Huang, Richard Xiong

This paper introduces a cost-effective robotic handwriting system designed to replicate human-like handwriting with high precision. Combining a Raspberry Pi Pico microcontroller, 3D-printed components, and a machine learning-based handwriting generation model implemented via TensorFlow, the system converts user-supplied text into realistic stroke trajectories. By leveraging lightweight 3D-printed materials and efficient mechanical designs, the system achieves a total hardware cost of approximately \$56, significantly undercutting commercial alternatives. Experimental evaluations demonstrate handwriting precision within $\pm$0.3 millimeters and a writing speed of approximately 200 mm/min, positioning the system as a viable solution for educational, research, and assistive applications. This study seeks to lower the barriers to personalized handwriting technologies, making them accessible to a broader audience.