多轮对话 RAG：把「那它呢」翻译成能检索的问题
用户第二轮问「那它支持导出吗」——这三个字没法直接检索。多轮对话 RAG 的核心动作是 condense：用对话历史把带指代、带省略的追问改写成独立完整的问题再去检索。本文讲清指代消解与历史压缩的做法、改写偏移的坑、以及「检索结果也要进历史」这个常被忽略的细节。
阅读全文 →
全部文章
ARCHIVE 共 383 条Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs
Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system kee…
Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys
We present a systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while l…
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation
Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in …
Enoki: Efficient Multi-Level Hallucination Detection
Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination dete…
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
Large language models often answer structurally unanswerable questions, such as computing cot(-540°) or evaluating (1).s…
HyQuant: Hybrid-Precision Quantization for LLM Attention
Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-b…
A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware
AI-powered search products such as ChatGPT search, Google's AI Overviews, and Perplexity provide LLM-synthesized answers…
GPT-5 发布：统一系统路由下一代旗舰
OpenAI 发布 GPT-5，将快速响应与深度推理统一到一个系统内自动路由，在编码、数学、多语言与幻觉抑制上全面提升，并大幅加强 Agentic 任务能力。
GPT-4o 发布：原生全模态与实时语音交互
OpenAI 发布 GPT-4o（'o' 为 omni），文本、音频、图像端到端统一训练，语音对话平均延迟降至 320 毫秒，接近人类对话反应速度。
OpenAI 发布 Sora：视频生成的 GPT-3 时刻
Sora 基于扩散模型与 Transformer 架构，可直接从文本生成长达一分钟的高保真视频，展示了对物理世界'世界模拟器'式的理解潜力。
GPT-4 发布：多模态与长上下文的分水岭
OpenAI 发布 GPT-4，支持图文多模态输入，在律师资格考试等专业基准上达到人类前 10% 水平，并引入 32K 长上下文版本。
← 上一页
第 32 / 32 页 · 共 383 条