AI 与机器学习2024arxiv.org
用 Binoculars 识别 LLM：零样本检测机器生成文本
Spotting LLMs with Binoculars: Zero-Shot Detection of Machine-Generated Text
进阶 · 约 30 分钟读完前置知识：Transformer 基础、语言模型困惑度、文本生成检测
导读
这篇论文提出 Binoculars 方法，无需训练即可零样本检测 LLM 生成的文本。其核心思路是比较两个不同 LLM 对同一段文本的困惑度差异，利用机器文本与人类文本在模型预测分布上的系统性区别来判别。
HN 关注点：LLM 生成文本泛滥，检测器关系到学术诚信、内容平台治理等，但 HN 读者普遍质疑此类检测器的误报率和可绕过性。
HN 评论精选
这几条评论里：质疑 1 补充 2 亲历 1
亲历检测器误报多且易绕过，模仿人类文本风格改写即可规避
我在这个领域做过大量实验。所有这些检测器 (a) 产生大量误报，(b) 只要懂行就极易绕过。比如让 LLM 逐段模仿一段真实人类文本的风格来改写，效果远好于让它'用某种风格写作'。另外一些细节：用词过于宽泛容易被人写文本被误判为 AI（所以用 Grammarly 润色被标记别奇怪）；反之，把少见表达替换成常见表达也能让 AI 文本更难被检出。我可以分享几百次实验的细节。
adaboese查看英文原文
I can talk a lot about this, since this is the space I've spent a lot in experimenting. All I will say is that all these detectors (a) create a ton of false-positives, and (b) are incredibly easy to bypass if you know what you are doing. As an example, one method that I found that works extremely well is to simply rewrite the article section by section with instructions that require to mimic the writing style of an arbitrary block of human written text. This works a lot better than (as an example) asking to write in a specific style. Like, if I just say something along the lines of "write in a casual style that conveys lightheartedness towards the topic" is not going to work as good as simply saying "rewrite mimicking the style in which the following text block is written X" (where X is an example of a block of human written text). There are some silly things that will (a) trigger human written text to be detected as a AI and (b) that allow to avoid AI detection, e.g. using broad dictionary tends to trigger AI bots to detect the text as written by AI. So if you are using Grammarly to "improve your writing", then don't be surprised if it gets flagged. The inverse is true too. If you some statistical analyzes to replace less common expressions with more common expressions, AI-text is less likely to be detected as AI. If someone is interested, I can talk a lot more about hundreds of experiments I've done by now.
补充方法原理可理解为检测偏离'人类均值'的文本，但对抗训练可能使其失效
外行解读：LLM 表现得像'人类的平均聚合'，而任何具体的人都会偏离均值。由于高维球体的体积几乎都在边缘，几乎没人像均值，所以误报率低？这是个聪明的方案，直到 LLM 做对抗性训练为止。
ISL查看英文原文
Is a layman's interpretation of this to state: LLMs tend to perform like aggregated humanity, but any given human will differ. Since all the volume of a high-dimensional sphere is at the edge, almost nobody is like the mean, so the false-positive-rate is low? It's a clever plan, until the LLMs do some adversarial training....
质疑对方法实际效果持怀疑态度
引用了 minimaxir 的推文链接，表示（该方法的实际表现）不太乐观。
vicgalle_查看英文原文
> https://twitter.com/minimaxir/status/1749893683137454194 Not very promising, though.
补充文本质量才是关键，检测的真正意义在于应对内容生产成本归零
如果文本写得好（总有一天会好），我不在乎是不是 LLM 写的；写得差，我也不在乎是不是人写的。唯一需要在意的是：LLM 让文本变得极其廉价，隐性的'工作量证明'信号失效了。开放论坛也许有一天需要按提交付费。
etwigg查看英文原文
If the text is good, and someday it will be, I don't care if an LLM wrote it. If it's bad, I don't care if a person wrote it. The only reason to care is that the implicit proof-of-work signal has broken because LLM text is so cheap. Open forums might need to be pay-per-submission someday...
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
历次讨论
- 2024Hacker News 讨论帖161 分 · 99 评
同领域还值得读
DeepSeek-R1：通过强化学习激励 LLM 的推理能力
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
研究如何用强化学习激励大语言模型的推理能力，提出 DeepSeek-R1，并探讨 RL 训练对模型推理表现的影响。
AI 与机器学习2025 · 1,351 分 · 1,056 评 · 引用 30进阶 · 约 80 分钟编辑精选1-bit LLM 时代：面向低成本计算的三值参数
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
提出用三值参数 {-1, 0, 1} 替代 LLM 中的浮点权重，即所谓“1-bit LLM”。
AI 与机器学习2024 · 1,040 分 · 447 评 · 引用 19进阶 · 约 45 分钟编辑精选DeepSeek-V3.2：推进开放大语言模型的前沿
DeepSeek-v3.2: Pushing the frontier of open large language models
这是 DeepSeek-V3.2 的技术报告，延续了 DeepSeek 开源权重模型的路线，目标是让开放模型继续逼近甚至追平前沿闭源模型。
AI 与机器学习2025 · 982 分 · 465 评进阶 · 约 90 分钟编辑精选通过自我对弈与通用强化学习掌握国际象棋和将棋（AlphaZero）
Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
DeepMind 的 AlphaZero 论文：用通用强化学习算法（自我博弈 + MCTS + 神经网络），从零开始仅数小时训练便在国际象棋和将棋上击败了世界顶级引擎 Stock…
AI 与机器学习2017 · 539 分 · 270 评 · 引用 13进阶 · 约 90 分钟编辑精选用强化学习发现更快的矩阵乘法算法
Discovering faster matrix multiplication algorithms with reinforcement learning
论文提出 AlphaTensor，用强化学习搜索矩阵乘法算法。
AI 与机器学习2022 · 518 分 · 111 评专业 · 约 90 分钟编辑精选