大语言模型（LLM）在各种应用领域中已经取得了显着的成功，但是它常常无法捕捉和掌握最新的事实知识。而另一方面，知识图（Knowledge ...

引言 推理LLMs背后什么原理，跟通用LLMs有什么区别？2024年，Scaling Law逐步见顶，业界普遍认为通用LLM走到“高原区”，进化乏力，除了多模态LLM还在日新月异。行业灯塔OpenAI也迟迟不发布GPT-5, ...

大语言模型（LLM）近年来在推荐系统和个性化问答中被广泛应用。为了追求更加个性化的用户体验，实现「千人千面」，将用户的历史点击序列融入LLM的输入中变得至关重要。最常见结合的方式是，将用户点击历史，利用特定的规则转化为自然语言文本，作为LLM的用户背 ...

DSPy shifts the paradigm for interacting with models from prompt hacking to high-level programming, making LLM applications ...

The process of discovering molecules that have the properties needed to create new medicines and materials is cumbersome and ...

LLMFP breaks this deadlock by reimagining planning as a constrained optimization problem, a mathematical process of finding ...

A new framework called METASCALE enables large language models (LLMs) to dynamically adapt their reasoning mode at inference time. This framework addresses one of LLMs’ shortcomings, which is using ...