Searcharxiv⌕ Search

arXiv subjects

Zhuang Li

Publications and source records attributed to Zhuang Li.

At least 37 records · Page 2Linked to original sources
arXiv2025

Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagery

Vision language models (VLMs) that enable natural language interaction with satellite imagery can democratize Earth observation by accelerating expert workflows, making data accessible to non-specialists, and enabling planet-scale automation. However, existing datasets focus mainly on short-term, high-resolution imagery from a limited number of satellites, overlooking low-resolution, multi-satellite, long-term archives, such as Landsat, that are essential for affordable and bias-robust global monitoring. We address this gap with Landsat30-AU, a large-scale vision-language dataset built from 30-meter resolution imagery collected by four Landsat satellites (5, 7, 8, and 9) over Australia, spanning more than 36 years. The dataset includes two components: Landsat30-AU-Cap, containing $196,262$ image-caption pairs, and Landsat30-AU-VQA, comprising 17,725 human-verified visual question answering (VQA) samples across eight remote sensing domains. Both datasets are curated through a bootstrapped pipeline that leverages generic VLMs with iterative refinement and human verification to ensure quality. Our evaluation of eight VLMs on our benchmark reveals that off-the-shelf models struggle to understand satellite imagery. The open-source remote-sensing VLM EarthDial achieves only 0.07 SPIDEr in captioning and a VQA accuracy of 0.48, highlighting the limitations of current approaches. Encouragingly, lightweight fine-tuning of Qwen2.5-VL-7B on Landsat30-AU improves captioning performance from 0.11 to 0.31 SPIDEr and boosts VQA accuracy from 0.74 to 0.87. Code and data are available at https://github.com/papersubmit1/landsat30-au.

cs.CV↗
arXiv2025

DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement

Vision-Language Models (VLMs) generate discourse-level, multi-sentence visual descriptions, challenging text scene graph parsers built for single-sentence caption-to-graph mapping. Current approaches typically merge sentence-level parsing outputs for discourse input, often missing phenomena like cross-sentence coreference, resulting in fragmented graphs and degraded downstream VLM task performance. We introduce a new task, Discourse-level text Scene Graph parsing (DiscoSG), and release DiscoSG-DS, a dataset of 400 expert-annotated and 8,430 synthesised multi-sentence caption-graph pairs. Each caption averages 9 sentences, and each graph contains at least 3 times more triples than those in existing datasets. Fine-tuning GPT-4o on DiscoSG-DS yields over 40% higher SPICE metric than the best sentence-merging baseline. However, its high inference cost and licensing restrict open-source use. Smaller fine-tuned open-source models (e.g., Flan-T5) perform well on simpler graphs yet degrade on denser, more complex graphs. To bridge this gap, we introduce DiscoSG-Refiner, a lightweight open-source parser that drafts a seed graph and iteratively refines it with a novel learned graph-editing model, achieving 30% higher SPICE than the baseline while delivering 86 times faster inference than GPT-4o. It generalises from simple to dense graphs, thereby consistently improving downstream VLM tasks, including discourse-level caption evaluation and hallucination detection, outperforming alternative open-source parsers. Code and data are available at https://github.com/ShaoqLin/DiscoSG .

cs.CL↗
arXiv2025

On the Reliability of Large Language Models for Causal Discovery

This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal discovery through three research questions. We examine: (i) the impact of memorization for accurate causal relation prediction, (ii) the influence of incorrect causal relations in pre-training data, and (iii) the contextual nuances that influence LLMs' understanding of causal relations. Our findings indicate that while LLMs are effective in recognizing causal relations that occur frequently in pre-training data, their ability to generalize to new or rare causal relations is limited. Moreover, the presence of incorrect causal relations significantly undermines the confidence of LLMs in corresponding correct causal relations, and the contextual information critically affects the outcomes of LLMs to discern causal connections between random variables.

cs.CL↗
arXiv2025

Text-Driven Video Style Transfer with State-Space Models: Extending StyleMamba for Temporal Coherence

StyleMamba has recently demonstrated efficient text-driven image style transfer by leveraging state-space models (SSMs) and masked directional losses. In this paper, we extend the StyleMamba framework to handle video sequences. We propose new temporal modules, including a \emph{Video State-Space Fusion Module} to model inter-frame dependencies and a novel \emph{Temporal Masked Directional Loss} that ensures style consistency while addressing scene changes and partial occlusions. Additionally, we introduce a \emph{Temporal Second-Order Loss} to suppress abrupt style variations across consecutive frames. Our experiments on DAVIS and UCF101 show that the proposed approach outperforms competing methods in terms of style consistency, smoothness, and computational efficiency. We believe our new framework paves the way for real-time text-driven video stylization with state-of-the-art perceptual results.

cs.GR↗
arXiv2025

Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base

The effectiveness of Large Language Models (LLMs) in legal reasoning is often limited due to the unique legal terminologies and the necessity for highly specialized knowledge. These limitations highlight the need for high-quality data tailored for complex legal reasoning tasks. This paper introduces LegalSemi, a benchmark specifically curated for legal scenario analysis. LegalSemi comprises 54 legal scenarios, each rigorously annotated by legal experts, based on the comprehensive IRAC (Issue, Rule, Application, Conclusion) framework from Malaysian Contract Law. In addition, LegalSemi is accompanied by a structured knowledge base (SKE). A series of experiments were conducted to assess the usefulness of LegalSemi for IRAC analysis. The experimental results demonstrate the effectiveness of incorporating the SKE for issue identification, rule retrieval, application and conclusion generation using four different LLMs.

cs.CL↗
arXiv2025

QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering

Review-based Product Question Answering (PQA) allows e-commerce platforms to automatically address customer queries by leveraging insights from user reviews. However, existing PQA systems generate answers with only a single perspective, failing to capture the diversity of customer opinions. In this paper we introduce a novel task Quantitative Query-Focused Summarization (QQSUM), which aims to summarize diverse customer opinions into representative Key Points (KPs) and quantify their prevalence to effectively answer user queries. While Retrieval-Augmented Generation (RAG) shows promise for PQA, its generated answers still fall short of capturing the full diversity of viewpoints. To tackle this challenge, our model QQSUM-RAG, which extends RAG, employs few-shot learning to jointly train a KP-oriented retriever and a KP summary generator, enabling KP-based summaries that capture diverse and representative opinions. Experimental results demonstrate that QQSUM-RAG achieves superior performance compared to state-of-the-art RAG baselines in both textual quality and quantification accuracy of opinions. Our source code is available at: https://github.com/antangrocket1312/QQSUMM

cs.CL↗
arXiv2025

LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews

Peer review is a cornerstone of quality control in scientific publishing. With the increasing workload, the unintended use of `quick' heuristics, referred to as lazy thinking, has emerged as a recurring issue compromising review quality. Automated methods to detect such heuristics can help improve the peer-reviewing process. However, there is limited NLP research on this issue, and no real-world dataset exists to support the development of detection tools. This work introduces LazyReview, a dataset of peer-review sentences annotated with fine-grained lazy thinking categories. Our analysis reveals that Large Language Models (LLMs) struggle to detect these instances in a zero-shot setting. However, instruction-based fine-tuning on our dataset significantly boosts performance by 10-20 performance points, highlighting the importance of high-quality training data. Furthermore, a controlled experiment demonstrates that reviews revised with lazy thinking feedback are more comprehensive and actionable than those written without such feedback. We will release our dataset and the enhanced guidelines that can be used to train junior reviewers in the community. (Code available here: https://github.com/UKPLab/acl2025-lazy-review)

cs.CL↗
arXiv2025

SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models

Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of training examples needed. However, the precise definition of style and the relationship between style, data quality, and LLM performance remains unclear. This research identifies two key stylistic elements in responses: linguistic form and instructional surprisal. We find that, among training data of comparable quality, higher consistency in these response elements leads to better LLM performance. Inspired by this, we introduce Style Consistency-Aware Response Ranking (SCAR), which automatically prioritizes instruction-response pairs in the training set based on their response stylistic consistency. By selecting the most style-consistent examples, using only 0.7% of the full dataset in the best case, the fine-tuned LLMs can match or even surpass the performance of models trained on the entire dataset in coding and open-ended question-answering benchmarks. Code and data are available at https://github.com/zhuang-li/SCAR .

cs.CL↗
arXiv2025

NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human

The widespread use of cloud-based Large Language Models (LLMs) has heightened concerns over user privacy, as sensitive information may be inadvertently exposed during interactions with these services. To protect privacy before sending sensitive data to those models, we suggest sanitizing sensitive text using two common strategies used by humans: i) deleting sensitive expressions, and ii) obscuring sensitive details by abstracting them. To explore the issues and develop a tool for text rewriting, we curate the first corpus, coined NAP^2, through both crowdsourcing and the use of large language models (LLMs). Compared to the prior works on anonymization, the human-inspired approaches result in more natural rewrites and offer an improved balance between privacy protection and data utility, as demonstrated by our extensive experiments. Researchers interested in accessing the dataset are encouraged to contact the first or corresponding author via email.

cs.CL↗
arXiv2025

Neural Influence Estimator: Towards Real-time Solutions to Influence Blocking Maximization

Real-time solutions to the influence blocking maximization (IBM) problems are crucial for promptly containing the spread of misinformation. However, achieving this goal is non-trivial, mainly because assessing the blocked influence of an IBM problem solution typically requires plenty of expensive Monte Carlo simulations (MCSs). This work presents a novel approach that enables solving IBM problems with hundreds of thousands of nodes and edges in seconds. The key idea is to construct a fast-to-evaluate surrogate model called neural influence estimator (NIE) offline as a substitute for the time-intensive MCSs, and then combine it with optimization algorithms to address IBM problems online. To this end, a learning problem is formulated to build the NIE that takes the false-and-true information instance as input, extracts features describing the topology and inter-relationship between two seed sets, and predicts the blocked influence. A well-trained NIE can generalize across different IBM problems given a social network, and can be readily combined with existing IBM optimization algorithms. The experiments on 25 IBM problems with up to millions of edges show that the NIE-based optimization method can be up to four orders of magnitude faster than MCSs-based optimization method to achieve the same optimization quality. Moreover, given a one-minute limit, the NIE-based method can solve IBM problems with up to hundreds of thousands of nodes, which is at least one order of magnitude larger than what can be solved by existing methods.

cs.NE↗
arXiv2025

BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks

The rapid growth of Large Language Models (LLMs) raises concerns about distinguishing AI-generated text from human content. Existing watermarking techniques, like \kgw, struggle with low watermark strength and stringent false-positive requirements. Our analysis reveals that current methods rely on coarse estimates of non-watermarked text, limiting watermark detectability. To address this, we propose Bipolar Watermark (\tool), which splits generated text into positive and negative poles, enhancing detection without requiring additional computational resources or knowledge of the prompt. Theoretical analysis and experimental results demonstrate \tool's effectiveness and compatibility with existing optimization techniques, providing a new optimization dimension for watermarking in LLM-generated content.

cs.LG↗
arXiv2025

Paragraph-to-Image Generation with Information-Enriched Diffusion Model

Text-to-image (T2I) models have recently experienced rapid development, achieving astonishing performance in terms of fidelity and textual alignment capabilities. However, given a long paragraph (up to 512 words), these generation models still struggle to achieve strong alignment and are unable to generate images depicting complex scenes. In this paper, we introduce an information-enriched diffusion model for paragraph-to-image generation task, termed ParaDiffusion, which delves into the transference of the extensive semantic comprehension capabilities of large language models to the task of image generation. At its core is using a large language model (e.g., Llama V2) to encode long-form text, followed by fine-tuning with LORA to alignthe text-image feature spaces in the generation task. To facilitate the training of long-text semantic alignment, we also curated a high-quality paragraph-image pair dataset, namely ParaImage. This dataset contains a small amount of high-quality, meticulously annotated data, and a large-scale synthetic dataset with long text descriptions being generated using a vision-language model. Experiments demonstrate that ParaDiffusion outperforms state-of-the-art models (SD XL, DeepFloyd IF) on ViLG-300 and ParaPrompts, achieving up to 15% and 45% human voting rate improvements for visual appeal and text faithfulness, respectively. The code and dataset will be released to foster community research on long-text alignment.

cs.CV↗
arXiv2025

VeriFix: Verifying Your Fix Towards An Atomicity Violation

Atomicity violation is one of the most serious types of bugs in concurrent programs. Synchronizations are commonly used to enforce atomicity. However, it is very challenging to place synchronizations correctly and sufficiently due to complex thread interactions and large input space. This paper presents \textsf{VeriFix}, a new approach for verifying atomicity violation fixes. Given a buggy trace that exposes an atomicity violation and a corresponding fix, % in the form of locks, \textsf{VeriFix} effectively verifies if the fix introduces sufficient synchronizations to repair the atomicity violation without introducing new deadlocks. The key idea is that \textsf{VeriFix} transforms the fix verification problem into a property verification problem, in which both the observed atomicity violation and potential deadlocks are encoded as a safety property, and both the inputs and schedules are encoded as symbolic constraints. By reasoning the conjoined constraints with an SMT solver, \textsf{VeriFix} systematically explores all reachable paths %from the whole schedule and input space and verifies if there exists a concrete \textit{schedule+input} combination to manifest the intended atomicity or any new deadlocks. We have implemented and evaluated \verifix\ on a collection of real-world C/C++ programs. The result shows that \textsf{VeriFix} significantly outperforms the state-of-the-art.

cs.SE↗
arXiv2025

Molecular Determinants of Orthosteric-allosteric Dual Inhibition of PfHT1 by Computational Assessment

To overcome antimalarial drug resistance, carbohydrate derivatives as selective PfHT1 inhibitor have been suggested in recent experimental work with orthosteric and allosteric dual binding pockets. Inspired by this promising therapeutic strategy, herein, molecular dynamics simulations are performed to investigate the molecular determinants of co-administration on orthosteric and allosteric inhibitors targeting PfHT1. Our binding free energy analysis capture the essential trend of inhibitor binding affinity to protein from published experimental IC50 data in three sets of distinct characteristics. In particular, we rank the contribution of key residues as binding sites which categorized into three groups based on linker length, size of tail group, and sugar moiety of inhibitors. The pivotal roles of these key residues are further validated by mutant analysis where mutated to nonpolar alanine leading to reduced affinities to different degrees. The exception was fructose derivative, which exhibited a significant enhanced affinity to mutation on orthosteric sites due to strong changed binding poses. This study may provide useful information for optimized design of precision medicine to circumvent drug-resistant Plasmodium parasites with high efficacy.

physics.bio-ph↗
arXiv2025

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment--factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca task (from 4.50 to 4.60), a 0.22 enhancement on the Just-eval benchmark (from 4.34 to 4.56), and a maximum improvement of 0.32 (from 3.53 to 3.85) on the MT-Bench dataset. We release the code and data at https://github.com/AnonymousCode-ComputerScience/RIDE.

cs.CL↗
arXiv2025

Evaluating and Predicting Distorted Human Body Parts for Generated Images

Recent advancements in text-to-image (T2I) models enable high-quality image synthesis, yet generating anatomically accurate human figures remains challenging. AI-generated images frequently exhibit distortions such as proliferated limbs, missing fingers, deformed extremities, or fused body parts. Existing evaluation metrics like Inception Score (IS) and Fréchet Inception Distance (FID) lack the granularity to detect these distortions, while human preference-based metrics focus on abstract quality assessments rather than anatomical fidelity. To address this gap, we establish the first standards for identifying human body distortions in AI-generated images and introduce Distortion-5K, a comprehensive dataset comprising 4,700 annotated images of normal and malformed human figures across diverse styles and distortion types. Based on this dataset, we propose ViT-HD, a Vision Transformer-based model tailored for detecting human body distortions in AI-generated images, which outperforms state-of-the-art segmentation models and visual language models, achieving an F1 score of 0.899 and IoU of 0.831 on distortion localization. Additionally, we construct the Human Distortion Benchmark with 500 human-centric prompts to evaluate four popular T2I models using trained ViT-HD, revealing that nearly 50\% of generated images contain distortions. This work pioneers a systematic approach to evaluating anatomical accuracy in AI-generated humans, offering tools to advance the fidelity of T2I models and their real-world applicability. The Distortion-5K dataset, trained ViT-HD will soon be released in our GitHub repository: \href{https://github.com/TheRoadQaQ/Predicting-Distortion}{https://github.com/TheRoadQaQ/Predicting-Distortion}.

cs.CV↗
arXiv2024

Natural Language Processing for Dialects of a Language: A Survey

State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dialect classification, sentiment analysis, parsing, and NLU benchmarks) and natural language generation (NLG) (for summarisation, machine translation, and dialogue systems). The survey is also broad in its coverage of languages which include English, Arabic, German, among others. We observe that past work in NLP concerning dialects goes deeper than mere dialect classification, and extends to several NLU and NLG tasks. For these tasks, we describe classical machine learning using statistical models, along with the recent deep learning-based approaches based on pre-trained language models. We expect that this survey will be useful to NLP researchers interested in building equitable language technologies by rethinking LLM benchmarks and model architectures.

cs.CL↗