Posts

All the articles I've posted.

• HyPerAlign: Hypotheses-driven Personalized Alignment

  Published: 4 May, 2025 |  at  04:32 PM

  

  65.01 🤔

  本文提出HyPerAlign方法，通过假设驱动的少样本学习实现LLM的个性化对齐，提高了模型对个体用户的适应性和安全性，同时减少了对微调的依赖。

• Exploring the Role of Diversity in Example Selection for In-Context Learning

  Published: 7 May, 2025 |  at  09:33 AM

  

  64.87 🤔

  本文提出基于多样性的上下文学习（DICL）方法，通过最大边际相关性（MMR）算法重新排序示例以平衡相关性和多样性，在多个数据集和大型语言模型上实现了约70%的下游任务性能提升或维持。

• Kimi-Audio Technical Report

  Published: 4 May, 2025 |  at  04:32 PM

  

  64.70 🤔

  本文提出Kimi-Audio，一个开源的音频基础模型，通过结合音频分词、LLM处理和逆分词的统一架构，以及大规模多模态训练，实现了音频理解、生成和对话的多任务SOTA性能。

• Waking Up an AI: A Quantitative Framework for Prompt-Induced Phase Transition in Large Language Models

  Published: 7 May, 2025 |  at  09:31 AM

  

  64.57 🤔

  本文提出了一种双重提示框架（TIP和TQP）来量化大型语言模型（LLMs）的认知相变，发现LLMs对概念融合提示的情感反应与人类直觉差异显著，揭示了AI与人类认知在概念整合上的潜在鸿沟。

• Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design

  Published: 12 May, 2025 |  at  11:08 AM

  

  64.27 🤔

  This position paper advocates for redesigning Large Language Models as 'reasonable parrots' that integrate argumentation theory principles to foster critical thinking through multi-persona dialogues, challenging users with diverse perspectives rather than providing one-sided answers.