A human-LLM collaborative pipeline yields EspanStereo, a multi-country Spanish stereotype dataset that exposes region-specific biases in Spanish LLMs and diverges sharply from English-centric resources.
On Evaluating and Mitigating Gender Biases in Multilingual Settings
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
citing papers explorer
-
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration
A human-LLM collaborative pipeline yields EspanStereo, a multi-country Spanish stereotype dataset that exposes region-specific biases in Spanish LLMs and diverges sharply from English-centric resources.
-
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.