Tag: Large Language Model
All the articles with the tag "Large Language Model".
-
HAIR: Hardness-Aware Inverse Reinforcement Learning with Introspective Reasoning for LLM Alignment
Published: at 11:12 AM
67.37 🤔HAIR introduces a novel LLM alignment method using hardness-aware inverse reinforcement learning and introspective reasoning, constructing a balanced safety dataset and training category-specific reward models with GRPO-S, achieving state-of-the-art harmlessness while preserving usefulness across multiple benchmarks.
-
Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
Published: at 04:29 PM 76.05 🤔本文提出MINDcraft框架和MineCollab基准，评估LLM在多代理具身协作中的性能，揭示了当前模型在通信和协调方面的局限性，并呼吁开发更先进的协作方法。
- Published: at 04:33 PM 75.58 🤔
本文通过提出位置 ID 操纵的 PFT 方法，揭示并解决了 LLM 在角色分离学习中依赖捷径的问题，提高了模型的鲁棒性和安全性，同时保持了性能。
-
ElChat: Adapting Chat Language Models Using Only Target Unlabeled Language Data
Published: at 04:28 PM 75.31 🤔本文提出ElChat方法，通过直接在目标无标签数据上适应聊天模型，并结合模型合并和权重复制技术，成功恢复聊天能力和指令遵循，同时在目标语言性能和安全方面表现出色。
-
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Published: at 04:28 PM 75.27 🤔本文提出WALL-E 2.0，一种无训练的神经符号学习方法，通过对齐LLM与环境动态构建精确世界模型，并结合模型预测控制框架，显著提升了LLM代理在开放世界任务中的性能。