Article

Fine-grained Debiasing for Large Language Modelsvia Bias Intensity and Probability Decoupling

2026-04-06

Abstract excerpt

<title>Abstract</title> <p>Large Language Models (LLMs) have demonstrated remarkable capabilities butoften inherit and even amplify social biases present in their training data. Existingdebiasing approaches—particularly those based on human preference alignment,such as Reinforcement Learning from Human Feedback (RLHF) and DirectPreference Optimization (DPO)—typically treat bias as a binary attribute, overlooking...

Topics

Open a Topic to create a Post that cites this publication.

Genomics and Rare Diseases

Identifiers and source

Literature Corpus work: 6dffe502-be67-5288-bc08-530d35b82c67
DOI: 10.21203/rs.3.rs-8984881/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Fine-grained Debiasing for Large Language Modelsvia Bias Intensity and Probability DecouplingDOI 10.21203/rs.3.rs-8984881/v1Read

Negative Preference Reduction in Large Language Model Unlearning: An Experimental ApproachSemantic proximity Read

SimLoRA for Enhanced Domain Specific LLM Fine Tuning Using Attention Weighted Low Rank Adaptation and RLHFSemantic proximity Read

Adaptive Contextual Preference Alignment for Large Language ModelsSemantic proximity Read

Screening Feedback for Language Models with Costly VerificationSemantic proximity Read

Noise-Robust Preference Alignment for Large Language Models via Confidence Estimation and Adaptive OptimizationSemantic proximity Read

Mechanism Design for Incentivizing User Feedback for Large Language ModelsSemantic proximity Read

Optimizing Human-Controlled Preference Alignment in Large Language Models via Dense Token Masking: A Methodological ApproachSemantic proximity Read

Unified Efficient Fine-Tuning Techniques for Open-Source Large Language ModelsSemantic proximity Read

A Survey of Large Language Models: Evolution, Architectures, Adaptation, Benchmarking, Applications, Challenges, and Societal ImplicationsSemantic proximity Read

CalibJudge: Calibrated LLM-as-a-Judge for Multilingual RAG with Uncertainty-Aware ScoringSemantic proximity Read

Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model AlignmentSemantic proximity Read

Upscaling A Smaller LLM to More Parameters via Manual Regressive DistillationSemantic proximity Read