Tag: LLM
All the papers with the tag "LLM".
LookAlike: Consistent Distractor Generation in Math MCQs
grok-3-latestScore: 0.68Published: at 19:18本文提出LOOK A LIKE方法,通过合成偏好对挖掘和交替优化策略,显著提高了数学多选题中干扰项和错误描述生成的一致性,超越了现有最先进方法。
$ extit{New News}$: System-2 Fine-tuning for Robust Integration of New Knowledge
grok-3-latestScore: 0.75Published: at 12:49本文提出 System-2 Fine-tuning(Sys2-FT)方法,通过自我生成数据显著提升大型语言模型对新知识的权重内学习能力,并揭示上下文遮蔽效应对微调的影响。
Structured Prompting and Feedback-Guided Reasoning with LLMs for Data Interpretation
grok-3-latestScore: 0.65Published: at 00:05本文提出 STROT 框架,通过结构化提示和反馈驱动的推理机制,显著提升大型语言模型在结构化数据分析中的可靠性、解释性和稳定性。
DeepCritic: Deliberate Critique with Large Language Models
grok-3-latestScore: 0.72Published: at 17:03本文提出 DeepCritic 框架,通过两阶段训练(监督微调与强化学习)显著提升大型语言模型在数学推理任务中的批判能力,为自动化监督和模型自我改进铺平道路。
On the generalization of language models from in-context learning and finetuning: a controlled study
grok-3-latestScore: 0.84Published: at 17:02本文通过控制实验揭示上下文学习在系统性泛化任务上优于微调,并提出通过上下文推理增强微调数据的方法,显著提升了微调的泛化能力。
Large Language Models Understanding: an Inherent Ambiguity Barrier
grok-3-latestScore: 0.75Published: at 16:55本文通过思想实验和半形式化论证,提出大型语言模型(LLMs)存在固有的模糊性障碍,无法将词汇与抽象概念关联,从而无法真正理解语言含义。