Tag: Reasoning
All the articles with the tag "Reasoning".
-
Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards
Published: at 11:15 AM
70.53 🤔REWARD-SQL introduces a framework for Text-to-SQL by decomposing queries into Chain-of-CTEs and using Process Reward Models (PRMs) with GRPO and Best-of-N sampling, achieving a state-of-the-art 68.9% execution accuracy on the BIRD dataset with a 7B model.
-
Llama-Nemotron: Efficient Reasoning Models
Published: at 11:30 PM 72.72 🤔NVIDIA 发布了 Llama-Nemotron 系列开放模型，通过结合神经架构搜索、知识蒸馏、持续预训练、基于高质量合成数据的多阶段有监督微调和大规模强化学习，构建了在推理能力和效率上均达到领先水平、并支持动态推理模式切换的异构模型家族。
-
Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
Published: at 04:33 PM 74.84 🤔本文提出LEPA自训练算法，通过训练LLM生成预期计划作为抽象元知识来提升问题解决泛化能力，并在多个推理基准上显著优于现有方法。
-
The dynamic interplay between in-context and in-weight learning in humans and neural networks
Published: at 11:20 PM 70.07 🤔本文通过神经网络中上下文学习（ICL）与权重学习（IWL）的动态交互，统一解释了人类学习中的组合性泛化、课程效应及灵活性与保留性权衡，为认知科学双过程理论提供了新视角。
-
Efficient Single-Pass Training for Multi-Turn Reasoning
Published: at 04:30 PM 74.08 🤔本文提出了一种通过响应令牌复制和自定义注意力掩码来实现多轮推理对话单次前向传递训练的方法，显著提高了训练效率，同时维护了推理可见性和位置一致性。