Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from an LLM verifier. However, judgment certainty varies substantially across criteria. Existing methods uniformly aggregate these judgments into a final...
Li-Cheng Pan, Hao Yang, Hao-Xuan Li et al.· 0 citations
It is found that, for a substantial fraction of incorrect joint predictions, the question-relevant unimodal branch can still recover the correct answer, suggesting that task-relevant evidence can remain recoverable from the relevant modality even when it is not reflected in the joint prediction.
Yu Mi, Li-Cheng Pan, Jia-Yi Zhu et al.· 0 citations
An automated single-prompt black-box jailbreak that shifts semantic assembly into the image plane by combining context-relevant scenes, scene-grounded textual carriers, and spatially distributed text fragments is proposed, which reveals a cross-modal safety gap in which harmful meaning emerges from the composition of i...
Zhi-Yi Mou, Yao Lu, Wang-Ze Ni et al.· arXiv.org· 0 citations
DeShortcut-Align is proposed, a shortcut-decoupling alignment framework that reduces dependence on superficial cues that significantly improves robustness against template-stripping bypass attacks, substantially reduces over-refusal, and better preserves general-purpose reasoning capabilities, thereby mitigating the al...
Qi-Rui Liu, Yi-Chen Sun, Yan Wang et al.· arXiv.org· 2 citations
Efficient On-Policy Self-Distilled Safety Alignment (EOPSA), which concentrates computational and gradient budgets exclusively on reliably supervised, safety-critical tokens, is proposed, consistently outperforming full-token distillation baselines in both safety compliance and reasoning retention.
Qi-Rui Liu, Yi-Chen Sun, Yan Wang et al.· 0 citations
This work introduces a process-centric diagnostic benchmark for AI-assisted peer review that compares the decision value of Gold-process variables and Predicted-process variables, and conducts stage-level evaluation, chain-consistency evaluation, and interventional sensitivity analysis.
Siming Yuan, Xue-Yi Zhang, Wang-Ze Ni 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.