13 papers
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
Hongyi Cen, Mingxin Wang, Yule Liu +3
Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, wea…
Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank
Suryaa Veerabathiran Seran, Ashwin Naresh Kumar, Tracy Holloway King +1
Adobe Express is expanding internationally, but the US has a disproportionately large content supply and interaction volume. Learning-to-rank (LTR) models trained primarily on beha…
On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models
Yule Liu, Yilong Yang, Jiale Teng +11
Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstruction capability that enables crea…
CHASM: Unveiling Covert Advertisements on Chinese Social Media
Jingyi Zheng, Tianyi Hu, Yule Liu +5
Current benchmarks for evaluating large language models (LLMs) in social media moderation completely overlook a serious threat: covert advertisements, which disguise themselves as…
TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding
Zifan Peng, Jingyi Zheng, Yule Liu +8
Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespre…
JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
Zifan Peng, Yule Liu, Zhen Sun +9
Large Audio Language Models (LALMs) have made significant progress. While increasingly deployed in real-world applications, LALMs face growing safety risks from jailbreak attacks t…