Failure to Mix: Large language models struggle to answer according to desired probability distrib...

文章核心总结与创新点

一、主要内容

本文聚焦大型语言模型(LLMs)在遵循目标概率分布生成输出方面的能力缺陷,通过系统性实验展开研究:

  1. 核心问题验证:以二元输出(“1"和"0”)的简单概率分布为起点,发现所有测试的LLMs(包括Gemini 2.5 Pro、GPT-5、Kimi K2等8种模型)均表现出"阶跃函数"行为——当目标概率p<50%时,"1"的输出率近乎0%;p>50%时近乎100%,即使调整温度参数(如拉满至2)也无实质改变。
  2. 多轮决策实验:当要求模型单次生成多个响应(D=2、3、10)时,前序响应仍保持阶跃函数特性,后续响应会通过"锯齿状"调整尝试补偿,但整体均值仅在D增大时趋近目标分布,且存在统计分布过窄等问题(如Qwen 3在p=0.15时98.8%的实验无"1"输出)。
  3. 复杂场景扩展:
    • 两参数离散分布(三选项输出)中,模型表现呈现强依赖性,输出规律混乱;
    • 词选择与位置偏差实验显示,LLMs存在固有偏好(如Gemini偏好"sun"而非"moon",多数模型偏好"1"而非"0"),但该偏差在p值仅1%的差异下会被覆盖;
    • 真实场景(生物信息学读数映射)和博弈论问题(非对称匹配硬币、商业定位游戏)中,模型能正确推理出最优概率策略,却仍无法执行,表现为阶跃函数或混乱响应。
  4. 解决方案探讨:提出两种低效的潜在方案——多轮连续
船载 OpenHarmony AIS 航海工作台:告警与防碰撞预警系统 船载OpenHarmony AIS航海工作台的告警与防碰撞系统,集成十余类告警(超速、偏航、会遇、SOS等),通过网格空间索引实现高效邻近判定,保障实时性。告警管理器统一调度规则、去重、通知与日志,支持悬浮球、语音、跑马灯、弹窗多渠道触达,确保航行安全。SOS紧急通道独立运行,避免干扰。系统设计强调性能优化与多场景适配,为航海安全提供核心支撑。 阅读详情

相关推荐

AI 应用开发:四维架构落地实战——以 HR Agent 为例拆解感知·推理·记忆·执行【意图路由、规划编排、长期记忆、工具执行、面试题】

本文基于四维架构(感知·推理·记忆·执行),以HR Agent为例,系统拆解大模型应用从“聊天”到“生产可用”的落地路径。通过Spring AI实现意图路由、规划编排、RAG检索与工具调用,结合真实踩坑复盘,揭示架构化设计对安全、成本与可维护性的关键价值,为AI Agent工程化提供可复用的实战框架。

王大师企业官方博客 1325

Java8动态生成SFunction:基于字段名的Lambda表达式实践

本文深入探讨了在Java8中如何基于字段名动态生成SFunction,以解决MyBatis Plus的LambdaQueryWrapper在动态查询场景下的局限性。通过核心原理LambdaMetafactory的解析和手把手的代码实现,展示了如何将字符串字段名转换为类型安全的Lambda表达式,从而实现真正动态、类型安全的查询条件构建与通用数据处理,显著提升代码的灵活性与安全性。

sss66的博客 955

Unity工业数据可视化:基于ModbusTCP的实时数据通信实战

本文详细介绍了在Unity中实现工业数据可视化的核心方法,重点讲解了基于ModbusTCP协议与PLC等工业设备进行实时数据通信的实战流程。内容涵盖NModbus库的集成、Modbus Slave模拟器的使用、TCP连接的建立与多线程安全通信、数据读写与解析,以及如何将实时数据驱动3D场景,为构建工业数字孪生与监控系统提供完整解决方案。

ol7890123的博客 555

Adversarial Texture for Fooling Person Detectors in the Physical World

本文提出了对抗纹理的想法(AdvTexture),与基本补丁攻击不同对抗纹理可以生成任意大小,可以覆盖任意大小的不了,并且纹理的任何局部都有对抗性的效果。当衣服被对抗纹理覆盖是,摄像头捕捉到的每一个局部区域都可以攻击探测器,这成功解决了片段缺失的问题。提出了一种两阶段生成方法:基于环形收割的可扩展生成攻击(TC-EGA)来制作广告纹理。第一阶段,训练一个全卷积网络FCN作为生成器,通过采样随机潜变量作为输入来产生纹理(不同于GAN中传统的生成器架构,每一层都使用卷积运算)......

weixin_49171105的博客 1068

调用D3D11硬解码和渲染VideoProcessor版本

在https://blog.csdn.net/robothn/article/details/78781321一文中使用shader来显示FFMPEG硬解码后的YUV420P,本文调用D3D11的videoprocessor来进行图像空间变换和尺寸变换,取得了较好的效果。 1.初始化D3D11设备、videodevice等数据结构 FFMPEG调用D3D11硬解码,获取其对应的device,videodevice。。。 FFMPEG使用av_hwdevice_find_type_by_name调用D3d11

zlyadvocate的博客 9291

网络调试和分析工具 Proxyman Premium

它支持MacOS、iOS和iPadOS等操作系统,提供丰富的功能,如查看和编辑HTTP/HTTPS请求和响应、设置断点、过滤请求等。Proxyman Premium还支持WebSocket、GraphQL和gRPC等现代网络协议调试,并通过直观且图形化的操作界面,使用户能高效地监控和操纵网络数据流。此外,它还具备多种高级功能,如WebSocket支持、DNS欺骗、自定义SSL证书等,为开发人员提供极大的便利。同时,由于软件版本更新和界面调整,上述步骤可能会有所变化,建议您参考最新版本的官方文档进行操作。

llhf688的博客 2005

Matlab实战:用递归最小二乘法(RLS)搞定动态系统参数辨识(附完整代码)

本文通过Matlab实战,详细介绍了如何利用递归最小二乘法(RLS)进行动态系统参数辨识。文章从理论优势切入,提供了完整的仿真数据生成、RLS算法核心实现代码,并对参数收敛过程、预测误差及不同遗忘因子的影响进行了可视化分析与性能评估,为工程实践提供了清晰的指南。

weixin_29035405的博客 505

VSCode 搭建C/C++编程环境 2025新版图文安装教程(VSCode安装 + C/C++环境搭建 + 运行测试 + 背景图设置)

100%搭建成功,VSCode 搭建C++编程环境 2025新版图文安装教程(VSCode安装+C++环境搭建+运行测试+背景图设置)

Code_流苏:在代码中寻诗意,在实践中觅真知 2976

解决RabbitMq登录时报出Not management user(Login failed)错误以及rabbitmqctl(RabbitMq)新增用户和用户角色权限

解决RabbitMq登录时报出Not management user(Login failed)错误以及rabbitmqctl(RabbitMq)查看用户权限、新增用户和用户角色权限。

念兮为美 7481

win10 跳过U8环境检测的IE WebControls.rar

win10 安装u8的时候 提示IE WebControls 不通过,这个工具可以欺骗u8的检查。 跳过U8环境检测的IE WebControls。提示导入失败后,重新检测通过。

IEM模型,地表粗糙度模拟

利用微波反演土壤水分时候,利用IEM模型可以实现对随机地表的模拟

jre9下载 jdk9

(Java SE Runtime Environment 9.0) 9.0u175 官方最新版 【x86|x64】

深度学习工具包 DeepLearningToolbox

深度学习工具包Deprecation notice.-----This toolbox is outdated and no longer maintained.There are much better tools available for deep learning than this toolbox, e.g. [Theano](http://deeplearning.net/software/theano/), [torch](http://torch.ch/) or [tensorflow](http://www.tensorflow.org/)I would suggest you use one of the tools mentioned above rather than use this toolbox.Best, Rasmus.DeepLearnToolbox================A Matlab toolbox for Deep Learning.Deep Learning is a new subfield of machine learning that focuses on learning deep hierarchical models of data.It is inspired by the human brain's apparent deep (layered, hierarchical) architecture.A good overview of the theory of Deep Learning theory is[Learning Deep Architectures for AI](http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf)For a more informal introduction, see the following videos by Geoffrey Hinton and Andrew Ng.* [The Next Generation of Neural Networks](http://www.youtube.com/watch?v=AyzOUbkUf3M) (Hinton, 2007)* [Recent Developments in Deep Learning](http://www.youtube.com/watch?v=VdIURAu1-aU) (Hinton, 2010)* [Unsupervised Feature Learning and Deep Learning](http://www.youtube.com/watch?v=ZmNOAtZIgIk) (Ng, 2011)If you use this toolbox in your research please cite [Prediction as a candidate for learning deep hierarchical models of data](http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6284)```@MASTERSTHESIS\{IMM2012-06284, author = "R. B. Palm", title = "Prediction as a candidate for learning deep hierarchical models of data", year = "2012",}```Contact: rasmusbergpalm at gmail dot comDirectories included in the toolbox-----------------------------------`NN/` - A library for Feedforward Backpropagation Neural Networks`CNN/` - A library for Convolutional Neural Networks`DBN/` - A library for Deep Belief Networks`SAE/` - A library for Stacked Auto-Encoders`CAE/` - A library for Convolutional Auto-Encoders`util/` - Utility functions used by the libraries`data/` - Data used by the examples`tests/` - unit tests to verify toolbox is workingFor references on each library check REFS.mdSetup-----1. Download.2. addpath(genpath('DeepLearnToolbox'));Example: Deep Belief Network---------------------```matlabfunction test_example_DBNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit RBM and visualize its weightsrand('state',0)dbn.sizes = [100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);figure; visualize(dbn.rbm{1}.W'); % Visualize the RBM weights%% ex2 train a 100-100 hidden unit DBN and use its weights to initialize a NNrand('state',0)%train dbndbn.sizes = [100 100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);%unfold dbn to nnnn = dbnunfoldtonn(dbn, 10);nn.activation_function = 'sigm';%train nnopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.10, 'Too big error');```Example: Stacked Auto-Encoders---------------------```matlabfunction test_example_SAEload mnist_uint8;train_x = double(train_x)/255;test_x = double(test_x)/255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit SDAE and use it to initialize a FFNN% Setup and train a stacked denoising autoencoder (SDAE)rand('state',0)sae = saesetup([784 100]);sae.ae{1}.activation_function = 'sigm';sae.ae{1}.learningRate = 1;sae.ae{1}.inputZeroMaskedFraction = 0.5;opts.numepochs = 1;opts.batchsize = 100;sae = saetrain(sae, train_x, opts);visualize(sae.ae{1}.W{1}(:,2:end)')% Use the SDAE to initialize a FFNNnn = nnsetup([784 100 10]);nn.activation_function = 'sigm';nn.learningRate = 1;nn.W{1} = sae.ae{1}.W{1};% Train the FFNNopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.16, 'Too big error');```Example: Convolutional Neural Nets---------------------```matlabfunction test_example_CNNload mnist_uint8;train_x = double(reshape(train_x',28,28,60000))/255;test_x = double(reshape(test_x',28,28,10000))/255;train_y = double(train_y');test_y = double(test_y');%% ex1 Train a 6c-2s-12c-2s Convolutional neural network %will run 1 epoch in about 200 second and get around 11% error. %With 100 epochs you'll get around 1.2% errorrand('state',0)cnn.layers = { struct('type', 'i') %input layer struct('type', 'c', 'outputmaps', 6, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %sub sampling layer struct('type', 'c', 'outputmaps', 12, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %subsampling layer};cnn = cnnsetup(cnn, train_x, train_y);opts.alpha = 1;opts.batchsize = 50;opts.numepochs = 1;cnn = cnntrain(cnn, train_x, train_y, opts);[er, bad] = cnntest(cnn, test_x, test_y);%plot mean squared errorfigure; plot(cnn.rL);assert(er<0.12, 'Too big error');```Example: Neural Networks---------------------```matlabfunction test_example_NNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);% normalize[train_x, mu, sigma] = zscore(train_x);test_x = normalize(test_x, mu, sigma);%% ex1 vanilla neural netrand('state',0)nn = nnsetup([784 100 10]);opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samples[nn, L] = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.08, 'Too big error');%% ex2 neural net with L2 weight decayrand('state',0)nn = nnsetup([784 100 10]);nn.weightPenaltyL2 = 1e-4; % L2 weight decayopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex3 neural net with dropoutrand('state',0)nn = nnsetup([784 100 10]);nn.dropoutFraction = 0.5; % Dropout fraction opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex4 neural net with sigmoid activation functionrand('state',0)nn = nnsetup([784 100 10]);nn.activation_function = 'sigm'; % Sigmoid activation functionnn.learningRate = 1; % Sigm require a lower learning rateopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex5 plotting functionalityrand('state',0)nn = nnsetup([784 20 10]);opts.numepochs = 5; % Number of full sweeps through datann.output = 'softmax'; % use softmax outputopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex6 neural net with sigmoid activation and plotting of validation and training error% split training data into training and validation datavx = train_x(1:10000,:);tx = train_x(10001:end,:);vy = train_y(1:10000,:);ty = train_y(10001:end,:);rand('state',0)nn = nnsetup([784 20 10]); nn.output = 'softmax'; % use softmax outputopts.numepochs = 5; % Number of full sweeps through dataopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, tx, ty, opts, vx, vy); % nntrain takes validation set as last two arguments (optionally)[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');```[![Bitdeli Badge](https://d2weczhvl823v0.cloudfront.net/rasmusbergpalm/deeplearntoolbox/trend.png)](https://bitdeli.com/free "Bitdeli Badge")

上一篇: A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases
下一篇: Bridging Human and Model Perspectives: A Comparative Analysis of Political Bias Detection in News...
UnknownBody
博客等级 码龄16年 5601粉丝 4754原创
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付:10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

UnknownBody

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值