Decision and Gender Biases in Large Language Models: A Behavioral Economic Perspective

文章总结与翻译

一、主要内容

本文从行为经济学视角,探究大型语言模型(LLMs)在决策中是否呈现人类的认知与社会偏见,通过两项经典实验(最后通牒博弈、赌博博弈)对Google Gemma-7B和Qwen-2.5-32B-Instruct-AWQ两款模型展开测试,核心内容如下:

  1. 实验设计:设置中性与性别条件提示(男性角色Joseph、女性角色Kelly),在最后通牒博弈中分析公平偏好(不公平厌恶参数α、优势不公平厌恶参数β),在赌博博弈中基于前景理论分析风险偏好(价值函数曲率α/β、损失厌恶系数λ、概率权重参数φ⁺/φ⁻),每项配置重复100次(温度参数设为1)以保证结果稳健性。
  2. 核心发现:
    • 模型决策介于完全理性与人类行为之间,偏见程度弱于人类:Gemma在最后通牒博弈中α≈0.454(低于人类的0.6-1.0)、β≈0.542(高于人类的0.2-0.3),呈现“β>α”的特殊模式(人类通常α>β),即更倾向于避免自身优势不公而非惩罚他人不公;Qwen在赌博博弈中λ≈1.542(低于人类的2.25),增益域接近风险中性,损失域存在温和损失厌恶。
    • 性别提示的影响具有场景依赖性:最后通牒博弈中,男性回应者使模型策略更稳定,女性提议者更具“他人导向”;赌博博弈中性别对参数估计无显著影响,说明性别差异主要体现在社交互动场景而非纯风险决策中。
  3. 结论:LLMs从训练数据中内化了人类的社会启发式,虽未被明确编程公平或风险偏好
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 712

MSP430开发入门:手把手教你用IAR EW430从建工程到烧录调试(附F5529配置)

本文详细介绍了如何使用IAR Embedded Workbench(EW430)进行MSP430F5529开发板的嵌入式开发,从环境搭建、工程配置到硬件调试全流程。通过实战示例和关键配置技巧,帮助开发者快速掌握MSP430开发的核心要点,包括LED控制、定时器使用和低功耗优化等实用技术。

weixin_30240349的博客 392

图像处理(12)--图像各种噪声及消除方法

文章目录结构1.什么是图像噪声2. 图像噪声来源3. 噪声分类及其消除方法3.1 高斯噪声及其消除方式3.1.1 如何确定一种噪声是高斯噪声3.1.2 高斯滤波消除高斯噪声3.1.3 高斯函数的重要性质3.2 瑞利噪声及其消除方式3.3 伽马(爱尔兰)噪声及其消除方式3.4 指数分布噪声及其消除方式3.5 均匀噪声及其消除方式3.6 脉冲(椒盐)噪声及其消除方式 1.什么是图像噪声 图像噪声是指...

ShaneHolmes 11万+

STM32CubeMX之emWin移植

“前面两章介绍了SDRAM和LTDC的使用,本篇文章将介绍emWin移植到STM32。”硬件环境:STM32F429IGT6软件环境:STM32CubeMX v5.5.0...

zhang062061的专栏 2827

ESP32 VSCode开发环境配置

ESP32 VSCode开发环境配置

qq_53529450的博客 511

【OpenCV C++】基本绘图操作

OpenCV C++基本绘图操作程序说明代码运行效果 程序说明 // 程序描述:OpenCV C++基本绘图操作 //参 考:毛星云《OpenCV3编程入门》 // 操作系统: Windows 10 64bit // 开发语言: C++ // IDE 版 本:Visual Studio 2019 // OpenCV版本:4.20 代码 main函数写法很简单,先创建空表Mat图像,然后点用函数绘制化学原子图,接着绘制组合图,最后显示图像。 //-------------------------

程序员,他们想的是什么?他们想的永远都是技术,他们崇尚的也永远都是技术。 766

全网最全RT-DETR涨点改进,基于官方源码1:1还原,在Ultralytics项目中配置rtdetr-r18、rtdetr-r34、rtdetr-r50、rtdetr-r101版本~小论文大论文必备

本文详细介绍了如何将RT-DETR的ResNet18/34/50/101/154版本移植到ultralytics项目中。主要内容包括:1) RT-DETR核心特点,如高效混合编码器、IoU感知查询选择等;2) 提供完整ResNet核心代码;3) 分步配置指南,包括创建模块文件和修改tasks.py;4) 各版本yaml配置文件的创建方法。该方案可帮助研究者快速实现RT-DETR改进,适用于目标检测相关论文研究。所有配置文件均可正常运行,为实验部署提供了便利。

Ai缝合怪、助力小伙伴高效发论文 3935

SAP-ABAP:SAP库存管理核心增强:IF_EX_MB_DOCUMENT_BADI 深度解析

SAP库存管理核心增强:IF_EX_MB_DOCUMENT_BADI 深度解析

baidu_35680696的博客 1447

C#上位机面试必问30题:机器视觉+工业通信+性能优化(含答案解析)

工业通信:围绕“稳定性”展开,重点答异常处理、断线重连、资源释放;机器视觉:围绕“精度+速度”展开,重点答预处理、ROI、参数优化;性能优化:围绕“UI不卡、内存不泄、效率不低”展开,重点答异步、限流、资源复用;面试加分项:结合实际项目案例(如“我在XX项目中用信号量解决了多设备并发卡顿问题”)。

这里只有干货:从 Modbus 通信到 MES 对接,从 YOLO 训练到工控机部署,带你搞定工业软件开发全流程。 1511

老版QQ原生表情gif动态

这是老版的QQ表情,不过全是动态的的,Windows照片查看器是不会动的,可以右击用浏览器打开查看,再说一遍是老版的,只是分享给宁愿用老版也要动态的人。

lwip-2.0.3

lwip是瑞典计算机科学院(SICS)的Adam Dunkels 开发的一个小型开源的TCP/IP协议栈。实现的重点是在保持TCP协议主要功能的基础上减少对RAM 的占用。

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")

精雕软件(JDpaint) 5.5 绿色版

精雕软件(JDpaint) 5.5 绿色版精雕软件(JDpaint) 5.5 绿色版精雕软件(JDpaint) 5.5 绿色版

上一篇: LLM Weekly(2026.7.6-2026.7.12)
下一篇: Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models
UnknownBody
博客等级 码龄16年 5601粉丝 4739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