This work formalizes polarity-aware evidence grounding: linking each response sentence to its contextual evidence with a supporting, contradicting, or irrelevant label, and proposes eTracer, a post-hoc framework whose context-aware signed scorer recovers the full evidence map in a single forward pass per response.
Bo-Hao Chu, Qianli Wang, Hendrik Damm et al.· 0 citations
Instead of post-hoc diagnosis, E-Closure is introduced to supervise three dependencies for reliable reasoning during training, combining generation supervision on supported original and counterfactual responses with bidirectional switching constraints.
Bo-Hao Chu, Hendrik Damm, Qianli Wang et al.· 0 citations
A metamodel-guided model generation method that coordinates generation-time constraints and post-generation validation and support coordinating generation constraints, domain checks, and task acceptance to construct models and guide bounded repair.
Tong Ma, Hui Lai, Hui Wang et al.· 3 citations· ⚡2
AI labels, typically implemented via underlying tracing mechanisms such as watermarks and metadata, are crucial for protecting Artificial Intelligence-Generated Content (AIGC) against security threats like disinformation and evasion. However, the perceived devaluation of AI-assisted work discourages creators from discl...
Shu-Ning Zhang, Hui Wang, Rongjun Ma et al.· 0 citations
Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support conflict verification tasks, we present ContraNote, a large-scale real-world dataset curated from X's Community Notes s...
Shu-Ning Zhang, D. Shi, Bo-Hao Chu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.