MAAM: Anchor-Preserving Compression and Contextual Calibration for Chinese Discriminatory Language Detection
Researchers have developed MAAM, a novel framework for detecting discriminatory language in Chinese. This model-agnostic approach uses a "visual blur" inspired mechanism to preserve key semantic anchors while calibrating them with contextual priors. MAAM also introduces ChLGBT, a new dataset specifically for identifying bias within the Chinese LGBT community, containing over 8,000 annotated samples. AI
IMPACT Offers a more compact and stable approach to detecting subtle bias in language, potentially reducing reliance on massive LLMs for specific tasks.