Results show that benchmark construction can alter a post-correction training decision and that support size alone does not characterize the remaining value of representation adaptation, and that support size alone does not characterize the remaining value of representation adaptation.
Ze-Xing Zhang, Ji-Chao Li, Tian-Yang Lei et al.· 0 citations
This work introduces Selective Posterior Margin Regularization (SPMR), which preserves the Forward objective and converts this disagreement into a graded update on the clean classifier and transfers to estimated transitions, human annotations, architectural changes, and stronger Forward recipes.
Ze-Xing Zhang, Ji-Chao Li, Tian-Yang Lei et al.· 0 citations
ADAM-Bench (Auditing Dialogue Assertions with Multimodal Evidence), a benchmark for paper-grounded hallucinations in scientific dialogue, is introduced and two tasks are defined: hallucination detection and minimal evidence set localization.
Ze-Xing Zhang, Tian-Yang Lei, Ke-Wei Yang et al.· Proceedings of the 32nd ACM...· 0 citations
AI reviewers can now produce many specific criticisms, but more criticism is not necessarily a better review. A review may miss a consequential weakness or retain an allegation that available evidence does not support. These failures require opposite corrections, yet generation-oriented systems and aggregate measures o...
Ze-Xing Zhang, Ji-Chao Li, Tian-Yang Lei et al.· 0 citations
Results indicate a feasible engineering pathway from perceptive DT functions toward reasoning-enabled collaborative decision support, and case-level evidence of improved cross-phase coordination under controlled disturbance scenarios is provided.
Zhu Xiang, Ming-Hao Li, Tian-Yang Lei et al.· Systems· 0 citations
Large language models (LLMs) and large multimodal models (LMMs) are increasingly applied in scientific dialogue, but it remains unclear whether they can reliably ground specific dialogue statements to paper-based evidence. A central challenge is paper-grounded hallucination under a paper-as-truth setting: statements th...
Zexing Zhang, Tianyang Lei, Kewei Yang et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.