Image de couverture de livre

Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cheng, Ruoxi, Ma, Haoxuan, Cao, Shuirong, Li, Jiaqi, Pei, Aihua, Wang, Zhiqiang, Ji, Pengliang, Wang, Haoyu, Huo, Jiaqi
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AGR: Age Group fairness Reward for Bias Mitigation in LLMs
par: Cao, Shuirong, et autres
Publié: (2024)

Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining
par: Cheng, Ruoxi, et autres
Publié: (2024)

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
par: Cheng, Ruoxi, et autres
Publié: (2024)

EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
par: Cheng, Ruoxi, et autres
Publié: (2025)

SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts
par: Pei, Aihua, et autres
Publié: (2024)

KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs
par: Pei, Aihua, et autres
Publié: (2024)

Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
par: Cheng, Ruoxi, et autres
Publié: (2025)

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment
par: Zhang, Jinghao, et autres
Publié: (2025)

Mitigating Gender Bias in Depression Detection via Counterfactual Inference
par: Hu, Mingxuan, et autres
Publié: (2025)

Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models
par: Chen, Feng, et autres
Publié: (2023)

Learning Universal Human Mobility Patterns with a Foundation Model for Cross-domain Data Fusion
par: Ma, Haoxuan, et autres
Publié: (2025)

Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs
par: Liu, Yifan, et autres
Publié: (2024)

Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling
par: Lv, Jiaqi, et autres
Publié: (2026)

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
par: Cheng, Ruoxi, et autres
Publié: (2026)

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
par: Zhao, Qinjian, et autres
Publié: (2025)

Beyond 9-to-5: A Generative Model for Augmenting Mobility Data of Underrepresented Shift Workers
par: Ma, Haoxuan, et autres
Publié: (2025)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
par: Li, Ang, et autres
Publié: (2025)

Composition Vision-Language Understanding via Segment and Depth Anything Model
par: Huo, Mingxiao, et autres
Publié: (2024)

Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching
par: Li, Zeqiao, et autres
Publié: (2026)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
par: Wang, Jiaqi, et autres
Publié: (2025)

Revealing Political Bias in LLMs through Structured Multi-Agent Debate
par: Bandaru, Aishwarya, et autres
Publié: (2025)

Structured Self-Consistency:A Multi-Task Evaluation of LLMs on VirtualHome
par: Xu, Jiaqi, et autres
Publié: (2026)

Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
par: Yu, Tianrun, et autres
Publié: (2025)

MobiVerse: Scaling Urban Mobility Simulation with Hybrid Lightweight Domain-Specific Generator and Large Language Models
par: Liu, Yifan, et autres
Publié: (2025)

DMRL: Data- and Model-aware Reward Learning for Data Extraction
par: Wang, Zhiqiang, et autres
Publié: (2025)

RUMAD: Reinforcement-Unifying Multi-Agent Debate
par: Wang, Chao, et autres
Publié: (2026)

Information-Preserving CSI Feedback: Invertible Networks with Endogenous Quantization and Channel Error Mitigation
par: Tian, Haotian, et autres
Publié: (2025)

Deep Reinforcement Learning for Digital Twin-Oriented Complex Networked Systems
par: Wen, Jiaqi, et autres
Publié: (2024)

Rethinking Spatio-Temporal Transformer for Traffic Prediction:Multi-level Multi-view Augmented Learning Framework
par: Lin, Jiaqi, et autres
Publié: (2024)

KnowBias: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
par: Pan, Jinhao, et autres
Publié: (2026)

Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning
par: Ma, Hao, et autres
Publié: (2025)

Fair Machine Unlearning: Data Removal while Mitigating Disparities
par: Oesterling, Alex, et autres
Publié: (2023)

Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI
par: Ma, Jiaqi W.
Publié: (2026)

Reinfier and Reintrainer: Verification and Interpretation-Driven Safe Deep Reinforcement Learning Frameworks
par: Yang, Zixuan, et autres
Publié: (2024)

Semantic Trajectory Data Mining with LLM-Informed POI Classification
par: Liu, Yifan, et autres
Publié: (2024)

Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration
par: Yang, Bo, et autres
Publié: (2026)

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
par: Zeqiao, Li, et autres
Publié: (2025)

PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs
par: Ranjan, Ravi, et autres
Publié: (2026)

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
par: Wang, Xingyao, et autres
Publié: (2023)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
par: Gao, Cheng, et autres
Publié: (2026)