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.
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
A hybrid fine-tuning objective using KL divergence for token calibration and Kahneman-Tversky optimization for semantic binding enables LLMs to produce outputs that match desired attribute distributions across repeated prompts.
citing papers explorer
-
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.
-
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
A hybrid fine-tuning objective using KL divergence for token calibration and Kahneman-Tversky optimization for semantic binding enables LLMs to produce outputs that match desired attribute distributions across repeated prompts.