semantic-reconstruction

该论文提出了一种名为"语义重构博弈"的免训练评估方法，用于更准确地评估 LLM 越狱攻击的成功率（ASR）。研究发现仅更换评判 LLM 就可导致 ASR 报告值相差高达 82 个百分点，而新方法通过将合规性判断分解为受限语义比较，显著降低了相对于人工标注的平均误差。

This paper introduces a semantic-aware completeness estimation method for robust multimodal sentiment analysis with incomplete modalities, aiming to improve accuracy when sentiment-related cues are missing.

This paper introduces a multi-feature fusion framework for semantic reconstruction from non-invasive brain recordings, combining static lexical (Word2Vec) and dynamic contextual (GPT) representations via cross-attention, achieving state-of-the-art performance in brain-to-text decoding.