Visual presentations are vital for effective communication. Early attempts to automate their creation using deep learning often faced issues such as poorly organized layouts, inaccurate text summarization, and a lack of image understanding, leading to mismatched visuals and text. These limitations restrict their application in formal contexts like business and scientific research. To address these challenges, we propose PreGenie, an agentic and modular framework powered by multimodal large language models (MLLMs) for generating high-quality visual presentations.PreGenie is built on the Slidev presentation framework, where slides are rendered from Markdown code. It operates in two stages: (1) Analysis and Initial Generation, which summarizes multimodal input and generates initial code, and (2) Review and Re-generation, which iteratively reviews intermediate code and rendered slides to produce final, high-quality presentations. Each stage leverages multiple MLLMs that collaborate and share information. Comprehensive experiments demonstrate that PreGenie excels in multimodal understanding, outperforming existing models in both aesthetics and content consistency, while aligning more closely with human design preferences.
论文检索
输入标题、作者或关键词，从 7,591 篇学术成果中精准定位
In recent years, intent classification technology based on In-Context Learning (ICL) has made significant progress. However, when applied to enterprise vertical domains, existing methods are inadequate in identifying micro-grained intentions. This study identifies two primary causes of errors in data analysis: (1) Retrieving incorrect instances, this is often due to the limitations of embedding models in capturing subtle sentence-level information in business scenarios (such as entity-related or phenomenon-specific details) (2) Insufficient reasoning ability of Large Language Models (LLMs), which tend to rely on surface-level semantics while overlooking deeper semantic associations and business logic, leading to misclassification. To address these issues, we propose ICLER, an intent classification method with enhanced reasoning. This method first optimizes the embedding model by introducing a reasoning mechanism to enhance its ability to fine-grained sentence-level information. Then, this mechanism is incorporated into the ICL framework, maintaining computational efficiency while significantly enhancing intent recognition accuracy. Experimental results demonstrate that ICLER significantly outperforms the original ICL method in intent identification within vertical domains. Moreover, it yields accuracy improvements of 0.04% to 1.14% on general datasets and its fine-tuned embedding model achieves an average performance gain of 5.56% on selected classification tasks in the MTEB benchmark.
NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretraining
PDF ↗Recent progress in multilingual pretraining has yielded strong performance on high-resource languages, albeit with limited generalization to genuinely low-resource settings. While prior approaches have attempted to enhance cross-lingual transfer through representation alignment or contrastive learning, they remain constrained by the extremely limited availability of parallel data to provide positive supervision in target languages. In this work, we introduce NeighXLM, a neighbor-augmented contrastive pretraining framework that enriches target-language supervision by mining semantic neighbors from unlabeled corpora. Without relying on human annotations or translation systems, NeighXLM exploits intra-language semantic relationships captured during pretraining to construct high-quality positive pairs. The approach is model-agnostic and can be seamlessly integrated into existing multilingual pipelines. Experiments on Swahili demonstrate the effectiveness of NeighXLM in improving cross-lingual retrieval and zero-shot transfer performance.
Adapting visual programming or prompting large language models (LLMs) to generate executable code for visual tasks like visual question answering (VQA) for specialized tasks or domains remains challenging due to high annotation and inference costs. We propose a low-cost visual program distillation method that can be used for models with at most 1 billion parameters and requires no human-generated program annotations. We achieve this through synthetic data augmentation based on decoupling programs into higher-level skills, called templates, and their corresponding arguments. Experimental results show that, with a relatively small amount of question/answer data, small language models can generate high-quality specialized visual programs with the added benefit of much faster inference.
Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment
PDF ↗Large language models (LLMs) have advanced virtual educators and learners, bridging NLP with AI4Education. Existing work often lacks scalability and fails to leverage diverse, large-scale course content, with limited frameworks for assessing pedagogic quality. To this end, we propose WikiHowAgent, a multi-agent workflow leveraging LLMs to simulate interactive teaching-learning conversations. It integrates teacher and learner agents, an interaction manager, and an evaluator to facilitate procedural learning and assess pedagogic quality. We introduce a dataset of 114,296 teacher-learner conversations grounded in 14,287 tutorials across 17 domains and 727 topics. Our evaluation protocol combines computational and rubric-based metrics with human judgment alignment. Results demonstrate the workflow’s effectiveness in diverse setups, offering insights into LLM capabilities across domains. Our datasets and implementations are fully open-sourced.
Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack execution-grounded supervision and offer limited support for iterative code correction, resulting in fragile and unreliable plot generation. We present **VisCode-200K**, a large-scale instruction tuning dataset for Python-based visualization and self-correction. It contains over 200K examples from two sources: (1) validated plotting code from open-source repositories, paired with natural language instructions and rendered plots; and (2) 45K multi-turn correction dialogues from Code-Feedback, enabling models to revise faulty code using runtime feedback. We fine-tune Qwen2.5-Coder-Instruct on VisCode-200K to create **VisCoder**, and evaluate it on PandasPlotBench. VisCoder significantly outperforms strong open-source baselines and approaches the performance of proprietary models like GPT-4o-mini. We further adopt a self-debug evaluation protocol to assess iterative repair, demonstrating the benefits of feedback-driven learning for executable, visually accurate code generation.
Generating high-quality question–answer (QA) pairs for specialized technical domains is essential for advancing knowledge comprehension, yet remains challenging. Existing methods often yield generic or shallow questions that fail to reflect the depth and structure of expert-written examples. We propose ExpertGenQA, a generation protocol that combines few-shot prompting with dual categorization by topic and question style to produce more diverse and cognitively meaningful QA pairs. ExpertGenQA achieves twice the efficiency of standard few-shot methods while maintaining 94.4% topic coverage. Unlike LLM-based judges, which often favor surface fluency, Bloom’s Taxonomy analysis shows that ExpertGenQA better captures expert-level cognitive complexity. When used to train retrieval systems, our questions improve top-1 accuracy by 13.02%, demonstrating their practical value for domain-specific applications.
MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation
PDF ↗Large Language Models (LLMs) hold significant promise for accelerating academic ideation but face critical challenges in grounding ideas and mitigating confirmation bias during refinement. To address these limitations, we propose MotivGraph-SoIQ, a novel framework that enhances LLM ideation by integrating a Motivational Knowledge Graph (MotivGraph), which provides essential grounding from research literature, with a Q-Driven Socratic Ideator. The Ideator, a dual-agent system utilizing Socratic questioning, facilitates a rigorous refinement process that mitigates confirmation bias and significantly improves idea quality across dimensions of novelty, experimental feasibility, and motivation. Our experimental results demonstrate MotivGraph-SoIQ’s effectiveness. Comparative studies show significant quantitative improvements over SOTA methods across LLM-based scoring, ELO ranking, and human evaluation. Ablation studies further validate the crucial contributions of both the MotivGraph for enhancing idea novelty and practicality, and the Socratic dialogue with the teacher agent for substantial quality improvement. This work underscores the potential of combining structured knowledge with interactive, critique-based refinement for robust LLM ideation.
As LLM-based agents become increasingly prevalent, triggers implanted in user queries or environment feedback can activate hidden backdoors, raising critical concerns about safety vulnerabilities in agents.However, traditional backdoor attacks are often detectable by safety audits that analyze the reasoning process of agents, hindering further progress in agent safety research.To this end, we propose a novel backdoor implantation strategy called Dynamically Encrypted Multi-Backdoor Implantation Attack. Specifically, we introduce dynamic encryption, which maps the backdoor into benign content, effectively circumventing safety audits.To enhance stealthiness, we further decompose the backdoor into multiple sub-backdoor fragments. Based on these advancements, backdoors are allowed to bypass safety audits significantly.Additionally, we present AgentBackdoorEval, a dataset designed for the comprehensive evaluation of agent backdoor attacks.Experimental results across multiple datasets demonstrate that our method achieves an attack success rate approaching 100% while maintaining a detection rate of 0%, illustrating its effectiveness in evading safety audits.Our findings highlight the limitations of existing safety mechanisms in detecting advanced attacks, underscoring the urgent need for more robust defenses against backdoor threats.Code and data are available at https://github.com/whfeLingYu/DemonAgent.
AuraDial: A Large-Scale Human-Centric Dialogue Dataset for Chinese AI Psychological Counseling
PDF ↗This paper introduces AuraDial, a large-scale, human-centric dialogue dataset for Chinese AI psychological counseling, comprising over 300,000 single-turn dialogues and 90,000 multi-turn dialogue sessions. A key distinction of AuraDial is its instruction set, primarily derived from real-world user queries, better reflecting genuine expression patterns compared to synthetic or template-based alternatives. Furthermore, we propose an innovative rephrasing-based data generation methodology designed to foster more human-like and empathetic responses, addressing a common shortcoming in AI-generated dialogue. Experimental results demonstrate that models fine-tuned on AuraDial significantly outperform those trained on other public datasets in generating empathetic and relevant replies. AuraDial offers a novel, valuable resource to the Chinese NLP community for advancing AI in psychological counseling. The dataset is publicly available at [https://huggingface.co/datasets/Mxode/AuraDial](https://huggingface.co/datasets/Mxode/AuraDial).
Short texts pose significant challenges for clustering due to semantic sparsity, limited context, and fuzzy category boundaries. Although recent contrastive learning methods improve instance-level representation, they often overlook local semantic structure within the clustering head. Moreover, treating semantically similar neighbors as negatives impair cluster-level discrimination. To address these issues, we propose Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering (FNSCC) framework. FNSCC incorporates neighborhood information at both the instance-level and cluster-level. At the instance-level, it excludes neighbors from the negative sample set to enhance inter-cluster separability. At the cluster-level, it introduces fuzzy neighborhood-aware weighting to refine soft assignment probabilities, encouraging alignment with semantically coherent clusters. Experiments on multiple benchmark short text datasets demonstrate that FNSCC consistently outperforms state-of-the-art models in accuracy and normalized mutual information. Our code is available at https://github.com/zjzone/FNSCC.
Health misinformation spreading online poses a significant threat to public health. Researchers have explored methods for automatically generating counterspeech to health misinformation as a mitigation strategy. Existing approaches often produce uniform responses, ignoring that the health literacy level of the audience could affect the accessibility and effectiveness of counterspeech. We propose a Controlled-Literacy framework using retrieval-augmented generation (RAG) with reinforcement learning (RL) to generate tailored counterspeech adapted to different health literacy levels. In particular, we retrieve knowledge aligned with specific health literacy levels, enabling accessible and factual information to support generation. We design a reward function incorporating subjective user preferences and objective readability-based rewards to optimize counterspeech to the target health literacy level. Experiment results show that Controlled-Literacy outperforms baselines by generating more accessible and user-preferred counterspeech. This research contributes to more equitable and impactful public health communication by improving the accessibility and comprehension of counterspeech to health misinformation.
Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesis
PDF ↗For individuals who have experienced traumatic events such as strokes, speech may no longer be a viable means of communication. While text-to-speech (TTS) can be used as a communication aid since it generates synthetic speech, it fails to preserve the user’s own voice. As such, face-to-voice (FTV) synthesis, which derives corresponding voices from facial images, provides a promising alternative. However, existing methods rely on pre-trained visual encoders, and finetune them to align with speech embeddings, which strips fine-grained information from facial inputs such as gender or ethnicity, despite their known correlation with vocal traits. Moreover, these pipelines are multi-stage, which requires separate training of multiple components, thus leading to training inefficiency. To address these limitations, we utilize fine-grained facial attribute modeling by decomposing facial images into non-overlapping segments and progressively integrating them into a multi-granular representation. This representation is further refined through multi-task learning of speaker attributes such as gender and ethnicity at both the visual and acoustic domains. Moreover, to improve alignment robustness, we adopt a multi-view training strategy by pairing various visual perspectives of a speaker in terms of different angles and lighting conditions, with identical speech recordings. Extensive subjective and objective evaluations confirm that our approach substantially enhances face-voice congruence and synthesis stability.
CrossQG: Improving Difficulty-Controllable Question Generation through Consistency Enhancement
PDF ↗Automatically generating questions with controlled difficulty has great application value, especially in the field of education. Although large language models are capable of generating questions of various difficulty levels, the generated questions often fail to align with the given target difficulty. To mitigate this issue, we propose CrossQG, a novel question generation method that requires no tuning of generator parameters, yet significantly improves difficulty consistency. Specifically, CrossQG consists of two steps: (1) contrast enhancement, which leverages questions from different difficulty levels to enhance the base models’ understanding of the target difficulty, and (2) cross filtering, which compares generated questions across different difficulty levels and filters out those that do not meet the target difficulty. We evaluate CrossQG on three high-quality question answering datasets. Experimental results demonstrate that across multiple models, CrossQG significantly outperforms several mainstream methods, achieving superior consistency with target difficulty and improving question quality. Notably, without generator training, CrossQG surpasses supervised fine-tuning in various instances.
Recent advances in large language models (LLMs) have significantly improved automated code generation, enabling tools such as GitHub Copilot and CodeWhisperer to assist developers in a wide range of programming tasks. However, the translation of complex mobile UI designs into high-fidelity front-end code remains a challenging and underexplored area, especially as modern app interfaces become increasingly intricate. In this work, we propose UIOrchestra, a collaborative multi-agent system designed for the AppUI2Code task, which aims to reconstruct static single-page applications from design mockups. UIOrchestra integrates three specialized agents, layout description, code generation, and difference analysis agent that work collaboratively to address the limitations of single-model approaches. To facilitate robust evaluation, we introduce APPUI, the first benchmark dataset for AppUI2Code, constructed through a human-in-the-loop process to ensure data quality and coverage. Experimental results demonstrate that UIOrchestra outperforms existing methods in reconstructing complex app pages and highlight the necessity of multi-agent collaboration for this task. We hope our work will inspire further research on leveraging LLMs for front-end automation. The code and data will be released upon paper acceptance.
In response to the urgent need for effective communication with crisis-affected populations, automated responses driven by language models have been proposed to assist in crisis communications. A critical yet often overlooked factor is the consistency of response style, which could affect the trust of affected individuals in responders. Despite its importance, few studies have explored methods for maintaining stylistic consistency across generated responses. To address this gap, we propose a novel metric for evaluating style consistency and introduce a fusion-based generation approach grounded in this metric. Our method employs a two-stage process: it first assesses the style of candidate responses and then optimizes and integrates them at the instance level through a fusion process. This enables the generation of high-quality responses while significantly reducing stylistic variation between instances. Experimental results across multiple datasets demonstrate that our approach consistently outperforms baselines in both response quality and stylistic uniformity.
The absence of explicit communication channels between automated vehicles (AVs) and other road users requires the use of external Human-Machine Interfaces (eHMIs) to convey messages effectively in uncertain scenarios. Currently, most eHMI studies employ predefined text messages and manually designed actions to perform these messages, which limits the real-world deployment of eHMIs, where adaptability in dynamic scenarios is essential. Given the generalizability and versatility of large language models (LLMs), they could potentially serve as automated action designers for the message-action design task. To validate this idea, we make three contributions: (1) We propose a pipeline that integrates LLMs and 3D renderers, using LLMs as action designers to generate executable actions for controlling eHMIs and rendering action clips. (2) We collect a user-rated Action-Design Scoring dataset comprising a total of 320 action sequences for eight intended messages and four representative eHMI modalities. The dataset validates that LLMs can translate intended messages into actions close to a human level, particularly for reasoning-enabled LLMs. (3) We introduce two automated raters, Action Reference Score (ARS) and Vision-Language Models (VLMs), to benchmark 18 LLMs, finding that the VLM aligns with human preferences yet varies across eHMI modalities. The source code, prompts, Blender scenarios, and rendered clips are available at https://github.com/ApisXia/AutoActionDesign.
System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries can exploit LLM vulnerabilities to expose these hidden prompts. To address this issue, we propose PromptKeeper, a defense mechanism designed to safeguard system prompts by tackling two core challenges: reliably detecting leakage and mitigating side-channel vulnerabilities when leakage occurs. By framing detection as a hypothesis-testing problem, PromptKeeper effectively identifies both explicit and subtle leakage. Upon leakage detected, it regenerates responses using a dummy prompt, ensuring that outputs remain indistinguishable from typical interactions when no leakage is present. PromptKeeper ensures robust protection against prompt extraction attacks via either adversarial or regular queries, while preserving conversational capability and runtime efficiency during benign user interactions.
Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with this subset achieves results comparable to or even exceeding those obtained using the entire dataset. However, most existing data selection techniques are designed for small-scale data pools, which fail to meet the demands of real-world SFT scenarios. In this paper, we replicated several self-scoring methods—those that do not rely on external model assistance—on two million-scale datasets, and found that nearly all methods struggled to significantly outperform random selection when dealing with such large-scale data pools. Moreover, our comparisons suggest that, during SFT, diversity in data selection is more critical than simply focusing on high-quality data. We also analyzed the limitations of several current approaches, explaining why they perform poorly on large-scale datasets and why they are unsuitable for such contexts. Finally, we found that filtering data by token length offers a stable and efficient method for improving results. This approach, particularly when training on long-text data, proves highly beneficial for relatively weaker base models, such as Llama3. The code is available at https://github.com/xiatingyu/SFT-DataSelection-at-scale.