Publications (12)
Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging
Zihang Fu, Haonan Wang, Jian Kang +2
Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from language-only pretraining. This trade…
Don't Change Me! User-Controllable Selective Paraphrase Generation
Mohan Zhang, Luchen Tan, Zhengkai Tu +4
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.…
TaleFrame: An Interactive Story Generation System with Fine-Grained Control and Large Language Models
Yunchao Wang, Guodao Sun, Zihang Fu +4
With the advancement of natural language generation (NLG) technologies, creative story generation systems have gained increasing attention. However, current systems often fail to a…
Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes
Zihang Fu, Fanxiao Li, Jianyang Gu +5
Large Language Model (LLM)-augmented Community Notes offer a scalable path for timely, evidence-grounded correction of health misinformation on social platforms. However, they stil…
InfoAffect: Affective Annotations of Infographics in Information Spread
Zihang Fu, Yunchao Wang, Chenyu Huang +2
Infographics are widely used in social media to convey complex information, yet how they influence users' affects remains underexplored due to the scarcity of relevant datasets. To…
Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation
Jiaying Wu, Zihang Fu, Haonan Wang +4
Community Notes, the crowd-sourced misinformation governance system on X (formerly Twitter), allows users to flag misleading posts, attach contextual notes, and rate the notes' hel…
Personalized Interpolation: Achieving Efficient Conversion Estimation with Flexible Optimization Windows
Xin Zhang, Weiliang Li, Rui Li +9
Optimizing conversions is crucial in modern online advertising systems, enabling advertisers to deliver relevant products to users and drive business outcomes. However, accurately…
Human-Computer Interaction and Visualization in Natural Language Generation Models: Applications, Challenges, and Opportunities
Yunchao Wang, Guodao Sun, Zihang Fu +1
Natural language generation (NLG) models have emerged as a focal point of research within natural language processing (NLP), exhibiting remarkable performance in tasks such as text…
From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs
Haonan Wang, Weida Liang, Zihang Fu +8
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…
Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents
Ruixue Zhang, Wei Yang, Luyun Lin +7
Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations…
MARCO: Click-Intent Decomposition for Calibrated Ads Conversion Prediction
Shiwen Shen, Xiru Huang, Liang Luo +32
Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), yet treats every click as the…
Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
Jiaying Wu, Fanxiao Li, Zihang Fu +2
The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators deliberately embed. Interpreting such creato…