2025_NIPS_Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decodi

文章核心总结与翻译

一、主要内容

该研究针对大型语言模型(LLMs)的幻觉问题(生成与预训练语料不一致的内容),提出了多模型对比解码(MCD)策略及配套机制,具体包括:

  1. 核心痛点:现有对比解码方法仅依赖单一易幻觉模型(邪恶模型)进行对比,虽能缓解幻觉,但对事实性内容的置信度不足,难以准确区分事实与幻觉token。
  2. 核心框架:
    • 训练阶段:通过反向直接偏好优化(CDPO)诱导幻觉生成邪恶模型,通过直接偏好优化(DPO)增强事实性生成真实模型;
    • 推理阶段:整合预训练模型、邪恶模型和真实模型的输出概率,构建多模型对比分布,放大事实token与幻觉token的概率差距;
    • 辅助机制:引入动态幻觉检测(逐token识别潜在幻觉)和树形修正机制(多路径探索并筛选最优事实路径),进一步降低幻觉。
  3. 实验验证:在TruthfulQA、FActScore、FACTOR(News/Expert/Wiki)三大基准测试中,MCD在开放式生成、多项选择、长文本生成等任务上均优于现有对比解码(CD、DoLa等)和表征编辑(CCS、ITI等)方法,显著提升模型输出的事实准确性。

二、创新点

  1. 提出多模型对比解码(MCD):首次整合邪恶模型(诱导幻觉)和真实模型(强化事实)进行对比,解决了单一对比模型置信度不足的问题,提升事实token的置
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 723

【R语言】富集分析可视化代码(整理版)

分别介绍了如何使用DAVID在线分析工具对基因进行GO/KEGG功能富集分析、使用R ggplot包对获得的基因GO/KEGG功能富集结果进行可视化、使用R clusterProfiler包和R AnnotationHub包对基因进行GO/KEGG功能富集分析、OrgDb包制作以及结果可视化等。故,我重新整理了一波,并补充了可对多个分组的富集结果进行可视化以及富集结果绘制圈图等的代码。关注“在打豆豆的小潘学长”公众号,发送“富集分析3”获得完整代码包和演示数据。一、单组富集结果可视化。

weixin_54004950的博客 1万+

开题报告该怎么写

考研即将来临,而一般很多大学都会选择在考研结束之后开始安排选题和开题报考(考研之前一般都不谈,老师也很人性化的,不愿意耽误你的复习) 但无论怎么推迟,我们最终都需要去面对并完成这些任务。 现在我就要教大家该如何写一个完整的开题报告! 准备模板。不同的学校有不同的格式,一般情况你的导师会给你们一个学校的标准格式,这个不用太费心。有了模板我们就可以按照模板的“线索”一步一步填充完成即可! 一般大致格式可谓: 研究背景/论文的目的、背景和意义 我们需要写明选择该题目的...

wuyueweifeng的博客 1097

ADRC自抗扰控制:工程抗扰“黑科技”,附C代码实战!

自抗扰控制(ADRC)是一种革新性的强鲁棒控制策略,通过主动估计和补偿系统扰动,无需精确数学模型即可实现优异控制性能。本文详细解析ADRC三大核心组件:跟踪微分器(TD)实现指令柔化,扩张状态观测器(ESO)实时估计总扰动,非线性状态反馈(NLSEF)完成动态补偿。针对二阶系统,文章提供完整的参数设计方法和C语言实现框架,包括关键函数fhan和fal的代码实现。ADRC将复杂对象"线性化"为积分器串联系统,显著提升抗扰能力,特别适用于电机控制、飞行器姿态等存在模型不确定性和强干扰的场景。

技术工作者 1737

VSLAM框架对比

格VSLAM特点介绍: (一)ORB-SLAM2 (二)ORB-SLAM3 (三)LSD-SLAM (四)

ljtx200888的博客 2295

LIO-SAM编译ubuntu20.04 Noetic

一、下载二、编译&&解决报错报错如下。

Kenneth666888的博客 689

博途S7-1200与昆仑通态MCGS纯仿真联调实战指南

本文详细介绍了博途S7-1200与昆仑通态MCGS纯仿真联调的实战指南,包括环境搭建、配置步骤、通信桥接及故障排除。通过TIA Portal和MCGS Pro搭建的仿真环境,可实现80%以上的基础功能验证,适用于工业自动化学习和开发,大幅降低硬件投入成本。

weixin_26834815的博客 439

解锁Gemini+Google Sheets/Excel:数据分析自动化新姿势

本文介绍了如何将谷歌AI工具Gemini集成到Google Sheets和Excel中进行智能数据分析。主要内容包括:1) Gemini的功能特点,具备语言理解和生成能力;2) 在Google Sheets中的集成步骤,包括订阅Workspace、开启Gemini功能及使用方法;3) 通过第三方插件在Excel中使用Gemini的方法;4) 销售和财务数据分析的实际案例;5) 使用时的注意事项,包括数据安全、问题处理和常见错误解决。通过Gemini集成,用户可以实现高效的数据处理和智能分析,提升工作效率。

远程部署调试 运行安装 项目调试 二次开发 项目技术新 持续迭代 部分源码免费分享 573

10、智慧变电站 - 加载vue大屏元素(整体效果)

这一篇文章非常简单,但是也非常出效果阅读前面几篇文章,都可以看到有顶部、左侧、右侧的面板,主要我不会录gif图片,大屏元素面板还有一些动态加载的效果。 vue的transition标签 Vue 提供了 transition 的封装组件,可以给任何元素和组件添加进入/离开过渡;在进入/离开的过渡中,会有 6 个 class 切换:v-enter 、v-enter-active 、v-enter-to 、v-leave 、v-leave-active 、v-leave-to。我们正好使用这个特性来达到面板进入

github_39988036的博客 1041

LinePhone3.2.7(android端最新版本) sip客户端

SIP客户端For android:LinePhone3.2.7(最新版本),官网地址:http://www.linphone.org/

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")

WINCC7.3破解文件

WINCC7.3硬件够破解文件,有需要的下载!WINCC7.3硬件够破解文件,有需要的下载!

计算机控制技术及应用

《计算机控制技术及应用》通过总结作者的科研成果和吸收国内外的先进理论、方法和技术,以计算机控制系统的网络化、开放化、智能化和集成化发展趋势为主线索,主要介绍计算机控制系统的基本概念和计算机控制系统的典型形式,计算机控制系统的数学描述与基本分析方法,以及数字PID控制器、最少拍控制系统、达林算法、状态变量设计法等设计方法及其各种改进算法。重点突出计算机控制系统输入输出通道接口的设计方法和典型控制系统的设计案例与实现方法等。

上一篇: 2025_NIPS_Memory Injection Attacks on LLM Agents via Query-Only Interaction
下一篇: 2025_NIPS_Reasoning Planning for 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