Tag: Reasoning
All the articles with the tag "Reasoning".
-
Efficient Reasoning for LLMs through Speculative Chain-of-Thought
Published: at 01:19 AM
79.97 🤔本文提出了推测思维链（SCoT）框架，通过轻量级草稿模型并行生成多个思维链草稿，并由微调后的目标大模型选择最佳草稿或决定重新思考，从而在保持接近大模型准确率的同时，显著降低了大型语言模型的推理延迟。
-
Toward Efficient Exploration by Large Language Model Agents
Published: at 04:31 PM 79.45 🤔本文通过使用 LLMs 显式实现后验采样 RL 算法，显著提高了 LLMs 代理在自然语言环境中的探索效率，同时保留了经典算法的统计性能优势。
-
Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing
Published: at 11:17 AM 79.35 🤔本文提出MegaBeam-Mistral-7B，通过渐进式训练和系统优化，使7B参数模型实现512K token长上下文处理，在多个基准测试中展现出与更大模型相当的性能，但多事实推理能力仍需改进。
-
HSI: Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models
Published: at 04:27 PM 78.97 🤔本文提出Head-Specific Intervention (HSI)方法，通过针对特定注意力头的激活干预，成功诱导Llama 2模型在AI协调行为上绕过安全对齐，效果优于监督微调和其它干预策略。
-
Accelerating Large Language Model Reasoning via Speculative Search
Published: at 11:12 AM 78.41 🤔Speculative Search (SpecSearch) accelerates LLM reasoning by up to 2.12× through a bi-level speculative thought generator that collaborates between small and large models, maintaining comparable reasoning quality via a quality-preserving rejection mechanism.