Zihang Fu

Zihang Fu, Fanxiao Li, Jianyang Gu et al.

Large Language Model (LLM)-augmented Community Notes offer a scalable path for timely, evidence-grounded correction of health misinformation on social platforms. However, they still reset at every post, leaving useful correction experience from prior cases unused. We introduce EvoNote, an agentic framework that enables health Community Notes generation to self-evolve through an evolving experience memory of prior misinformation correction episodes. Its core is fine-grained credit assignment: EvoNote grounds trajectory-level feedback in health-specific note qualities and distills it into action-level memory for claim analysis, evidence acquisition, and note writing. We evaluate EvoNote on MM-HealthCN, a 1.2K-instance multimodal benchmark of user-flagged health posts with human-written Community Notes and crowd-derived helpfulness labels. Under a human-validated hierarchical utility judge, EvoNote-generated notes are preferred over corresponding human-written notes in 89.6% of cases; on a separate set of Needs More Ratings posts without a crowd helpfulness verdict, EvoNote produces helpful notes for 82.0% of cases. It also reduces the median time needed to produce a candidate correction from over 13 hours in the human-note pipeline to under 2 minutes. Analyses link these gains to stronger evidence use and reusable correction strategies, positioning self-evolving note generation as a promising paradigm for health misinformation governance.

Yunchao Wang, Guodao Sun, Zihang Fu et al.

With the advancement of natural language generation (NLG) technologies, creative story generation systems have gained increasing attention. However, current systems often fail to accurately translate user intent into satisfactory story outputs due to a lack of fine-grained control and unclear input specifications, limiting their applicability. To address this, we propose TaleFrame, a system that combines large language models (LLMs) with human-computer interaction (HCI) to generate stories through structured information, enabling precise control over the generation process. The innovation of TaleFrame lies in decomposing the story structure into four basic units: entities, events, relationships, and story outline. We leverage the Tinystories dataset, parsing and constructing a preference dataset consisting of 9,851 JSON-formatted entries, which is then used to fine-tune a local Llama model. By employing this JSON2Story approach, structured data is transformed into coherent stories. TaleFrame also offers an intuitive interface that supports users in creating and editing entities and events and generates stories through the structured framework. Users can control these units through simple interactions (e.g., drag-and-drop, attach, and connect), thus influencing the details and progression of the story. The generated stories can be evaluated across seven dimensions (e.g., creativity, structural integrity), with the system providing suggestions for refinement based on these evaluations. Users can iteratively adjust the story until a satisfactory result is achieved. Finally, we conduct quantitative evaluation and user studies that demonstrate the usefulness of TaleFrame. Dataset available at https://huggingface.co/datasets/guodaosun/tale-frame.

Zihang Fu, Yunchao Wang, Chenyu Huang et al.

Infographics are widely used to convey complex information, yet their affective dimensions remain underexplored due to the scarcity of data resources. We introduce a 3.5k-sample affect-annotated InfoAffect dataset, which combines textual content with real-world infographics. We first collect the raw data from six domains and aligned them via preprocessing, the accompanied-text-priority method, and three strategies to guarantee the quality and compliance. After that we construct an affect table and use it to constrain annotation. Five state-of-the-art multimodal large language models (MLLMs) then analyze both modalities, and their outputs are fused with Reciprocal Rank Fusion (RRF) algorithm to yield robust affects and confidences. We conducted a user study with two experiments to validate usability and assess InfoAffect dataset using the Composite Affect Consistency Index (CACI), achieving an overall score of 0.986, which indicates high accuracy.

Zihang Fu, Haonan Wang, Jian Kang et al.

Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from language-only pretraining. This trade-off is especially pronounced in video-language models (VLMs), where visual alignment can impair temporal reasoning (TR) over sequential events. We propose MERIT, a training-free, task-driven model merging framework for restoring TR in VLMs. MERIT searches over layer-wise self-attention merging recipes between a VLM and its paired text-only backbone using an objective that improves TR while penalizing degradation in temporal perception (TP). Across three representative VLMs and multiple challenging video benchmarks, MERIT consistently improves TR, preserves or improves TP, and generalizes beyond the search set to four distinct benchmarks. It also outperforms uniform full-model merging and random layer selection, showing that effective recovery depends on selecting the right layers. Interventional masking and frame-level attribution further show that the selected layers are disproportionately important for reasoning and shift model decisions toward temporally and causally relevant evidence. These results show that targeted, perception-aware model merging can effectively restore TR in VLMs without retraining.

Jiaying Wu, Zihang Fu, Haonan Wang et al.

Community Notes, the crowd-sourced misinformation governance system on X (formerly Twitter), enables users to flag misleading posts, attach contextual notes, and vote on their helpfulness. However, our analysis of 30.8K health-related notes reveals significant latency, with a median delay of 17.6 hours before the first note receives a helpfulness status. To improve responsiveness during real-world misinformation surges, we propose CrowdNotes+, a unified framework that leverages large language models (LLMs) to augment Community Notes for faster and more reliable health misinformation governance. CrowdNotes+ integrates two complementary modes: (1) evidence-grounded note augmentation and (2) utility-guided note automation, along with a hierarchical three-step evaluation that progressively assesses relevance, correctness, and helpfulness. We instantiate the framework through HealthNotes, a benchmark of 1.2K helpfulness-annotated health notes paired with a fine-tuned helpfulness judge. Experiments on fifteen LLMs reveal an overlooked loophole in current helpfulness evaluation, where stylistic fluency is mistaken for factual accuracy, and demonstrate that our hierarchical evaluation and LLM-augmented generation jointly enhance factual precision and evidence utility. These results point toward a hybrid human-AI governance model that improves both the rigor and timeliness of crowd-sourced fact-checking.

Haonan Wang, Weida Liang, Zihang Fu et al.

Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this paradox using high-quality reasoning traces from DeepSeek-R1 as demonstrations and find that adding more exemplars consistently degrades accuracy, even when demonstrations are optimal. A detailed analysis reveals two mechanisms behind this decline: (i) semantic misguidance, where high textual similarity leads the model to treat the target as the same as the exemplar and to copy intermediate steps verbatim; and (ii) strategy transfer failure, where the model struggles to extract useful reasoning strategies and apply them to target questions. Guided by these, we introduce Insight-to-Solve (I2S), a sequential test-time procedure that turns demonstrations into explicit, reusable insights and derives a target-specific reasoning trace; optionally, the reasoning is self-refined for coherence and correctness (I2S+). Extensive experiments on diverse benchmarks show that I2S and I2S+ consistently outperform both direct answering and test-time scaling baselines across open- and closed-source models. Even for GPT models, our method helps: on AIME'25, GPT-4.1 rises by +14.0%, and o1-mini improves by +2.7% on AIME and +1.7% on GPQA, indicating that in-context demonstrations can be harnessed effectively via insight-refine-solve framework.

Jiaying Wu, Fanxiao Li, Zihang Fu et al.

The impact of misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators deliberately embed. Interpreting such creator intent is therefore essential for multimodal misinformation detection (MMD) and effective information governance. To this end, we introduce DeceptionDecoded, a large-scale benchmark of 12,000 image-caption pairs grounded in trustworthy reference articles, created using an intent-guided simulation framework that models both the desired influence and the execution plan of news creators. The dataset captures both misleading and non-misleading cases, spanning manipulations across visual and textual modalities, and supports three intent-centric tasks: (1) misleading intent detection, (2) misleading source attribution, and (3) creator desire inference. We evaluate 14 state-of-the-art vision-language models (VLMs) and find that they struggle with intent reasoning, often relying on shallow cues such as surface-level alignment, stylistic polish, or heuristic authenticity signals. These results highlight the limitations of current VLMs and position DeceptionDecoded as a foundation for developing intent-aware models that go beyond shallow cues in MMD.

Xin Zhang, Weiliang Li, Rui Li et al.

Optimizing conversions is crucial in modern online advertising systems, enabling advertisers to deliver relevant products to users and drive business outcomes. However, accurately predicting conversion events remains challenging due to variable time delays between user interactions (e.g., impressions or clicks) and the actual conversions. These delays vary substantially across advertisers and products, necessitating flexible optimization windows tailored to specific conversion behaviors. To address this, we propose a novel \textit{Personalized Interpolation} method that extends existing models based on fixed conversion windows to support flexible advertiser-specific optimization windows. Our method enables accurate conversion estimation across diverse delay distributions without increasing system complexity. We evaluate the effectiveness of the proposed approach through extensive experiments using a real-world ads conversion model. Our results show that this method achieves both high prediction accuracy and improved efficiency compared to existing solutions. This study demonstrates the potential of our Personalized Interpolation method to improve conversion optimization and support a wider range of advertising strategies in large-scale online advertising systems.

Mohan Zhang, Luchen Tan, Zhengkai Tu et al.

In the paraphrase generation task, source sentences often contain phrases that should not be altered. Which phrases, however, can be context dependent and can vary by application. Our solution to this challenge is to provide the user with explicit tags that can be placed around any arbitrary segment of text to mean "don't change me!" when generating a paraphrase; the model learns to explicitly copy these phrases to the output. The contribution of this work is a novel data generation technique using distant supervision that allows us to start with a pretrained sequence-to-sequence model and fine-tune a paraphrase generator that exhibits this behavior, allowing user-controllable paraphrase generation. Additionally, we modify the loss during fine-tuning to explicitly encourage diversity in model output. Our technique is language agnostic, and we report experiments in English and Chinese.

Ruixue Zhang, Wei Yang, Luyun Lin et al.

Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than "standard" information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than 100 documents) are sufficient to achieve reasonable accuracy. We integrate our models into an end-to-end cloud platform that provides both an easy-to-use annotation interface as well as an inference interface that allows users to upload documents and inspect model outputs.