自适应、去偏差、一致性兼备的LLM评判新框架，解决模型偏好与不公平评分问题
arXiv:2602.06625v2 Announce Type: replace Abstract: Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to t…
提出基于不确定性的大模型去偏与遗忘新方法，有效解决数据污染问题。
arXiv:2606.23313v1 Announce Type: cross Abstract: Benchmark-based evaluation is the dominant paradigm for assessing large language model (LLM) capabil…
让大模型避免框架效应影响，从隐藏偏见走向真正公平
arXiv:2602.04306v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuri…
ICLR 2026 顶会论文：用信息论指导消除奖励模型中的归纳偏置，为强化学习对齐提供更客观的评估基础
arXiv:2512.23461v2 Announce Type: replace Abstract: Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align la…
针对全模态语言模型的视觉捷径问题，提出分阶段后训练与视觉去偏评估方法，提升多模态理解的真实性
arXiv:2605.12034v2 Announce Type: replace-cross Abstract: Omni-modal language models are intended to jointly understand audio, visual inputs, and lang…
无需微调，RAG为LLM公平生成开辟新路径，有效减少偏见与幻觉。
arXiv:2605.16113v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved unprecedented success due to their exceptional generative…
揭示视觉语言模型语言压倒视觉导致幻觉的根源，提出几何去偏方法提升可靠性。
arXiv:2605.08245v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imag…
经典Double Q-learning的深度强化学习新范式，通过完全解耦动作选择与评估彻底消除最大化偏差。
arXiv:2507.00275v2 Announce Type: replace-cross Abstract: Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q…