Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

本文是LLM系列文章,针对《Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?》的翻译。

大型语言模型能检测长链思维推理中的错误吗?

摘要

最近,类似 o1 的模型备受关注,这些模型通过生成冗长的思维链(CoT)推理步骤来提升现有大语言模型(LLMs)的推理能力。在本文中,为了理解这些长思维链的质量,并衡量现有大语言模型对这些长思维链的批判能力,我们引入了 DeltaBench。它包含了不同类似 o1 的模型(如 QwQ、DeepSeek - R1)针对不同推理任务(如数学、代码、通用推理)生成的长思维链,用于衡量在长思维链推理中检测错误的能力。基于 DeltaBench,我们首先对生成的长思维链进行了细粒度分析,以探究不同类似 o1 模型的有效性和效率。然后,我们对现有的过程奖励模型(PRMs)和批判模型进行了广泛评估,以检测每个注释过程中的错误,旨在研究现有过程奖励模型和批判模型的界限与局限性。最后,我们希望 DeltaBench 能够帮助开发者更好地理解他们模型的长思维链推理能力。

引言

在这里插入图片描述
近年来,大语言模型(LLMs)取得了显著进展。在这些进展中,类似 o1 的大语言模型通过生成冗长的思维链(CoT)推理步骤,极大地提升了推理能力。
然而,尽管类似 o1 的模型及其长思维链推理方法越来越受欢迎,但对生成的推理链的质量和有效性的系统评估尚未得到充分研究,这给理解这些模型的能力和局限性带来了重大挑战。此外,随着大语言模型的不断发展,进一步提升其性能变得越来越具有挑战性。在这方面,一个关键的关注领域是批判能力的发展,即衡量为其他模型甚至自身生成的解决方案提

「文智助手」全场景办公AI助理AI+OPC全流程实践方案(大赛作品) 阅读详情

相关推荐

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。

专注于计算机研发知识和资讯分享 193

别再自己写消息提示了!5分钟用WPF+Material Design打造专业级Snackbar(支持.NET 6)

本文为WPF开发者提供了一份快速集成专业级Snackbar消息提示的实战指南。通过引入MaterialDesignThemes开源库,在.NET 6 WPF项目中,仅需5分钟即可告别传统的MessageBox,实现遵循Material Design规范、动画流畅、支持队列管理的非侵入式Snackbar控件,显著提升应用的用户体验与现代化交互水平。

year5的博客 173

Ollama+FAISS+Embedding+Rerank+LLM 详细部署指南

下载安装Ollama 双击运行安装程序 安装完成后会自动启动服务 修改默认安装路径(避免C盘爆满) 或使用PowerShell: 验证安装 Linux系统部署: (二)准备模型 1. 拉取Embedding模型 2. 拉取LLM模型 注意:原文中提到的可能需要从自定义仓库拉取: 3. 下载Rerank模型 (三)安装依赖库 创建项目目录和虚拟环境: 二、主要功能实现 项目结构 (一)配置文件(config/config.yaml) (二)文本分块策略实现 创建 : (三)文档读取

AI技术改变世界 1582

【亲测有效】OpenClaw Gateway 出现 “(no output)“ 卡死问题完整解决指南:从手动重启到 systemd Watchdog 自动恢复

最近在使用 OpenClaw(自托管 AI 助手框架,前身 Clawdbot/Moltbot)时,遇到了一个非常常见的顽疾:TUI(终端界面)或 Telegram 等通道经常显示 "(no output)",消息发出去后机器人完全没反应,看起来像是卡死了。

hampeter的博客 8610

【VAE学习笔记】全面通透地理解VAE(Variational Auto Encoder)

完整笔记:http://www.gwylab.com/note-vae.html 李宏毅老师的教程视频:https://www.bilibili.com/video/av15889450/?p=33 —————————————————————————————————   依据李宏毅老师的讲解,我整理了一番VAE的笔记。先简单介绍一下VAE,VAE作为一个生成模型,其基本思路是很容易理解的:把一堆真...

a312863063的博客 14万+

Zabbix在Ubuntu 22.04上的性能优化与监控实战:从基础安装到高级配置

本文详细介绍了在Ubuntu 22.04系统上部署和优化Zabbix监控系统的完整流程,从基础安装到高级配置。内容包括MySQL数据库设置、Zabbix服务器与Web前端优化、性能调优策略以及实战监控场景应用,帮助用户构建高效的企业级监控解决方案。

sss66的博客 895

LangChain Message 官方文档

消息是聊天模型中的基本通信单位。它们用于表示聊天模型的输入和输出,以及与对话相关的其他上下文或元数据。每条消息都包含一个角色(如“用户”、“助手”)和内容(如文本或多模态数据),并可能包含根据不同聊天模型提供商而有所不同的附加元数据。LangChain 提供了一个统一的消息格式,可以跨不同聊天模型使用,简化用户在不同模型之间切换时所需关注的消息格式差异。

AI Agent 首席体验官 896

生成模型实战 | StyleGAN详解与实现

StyleGAN 能够生成非常高分辨率人脸图像的关键在于,在增加分辨率的步骤中逐步增加生成网络和判别网络的复杂性,以便在每一步中,两个模型都可以很好地完成任务。我们学习了如何通过确保每个分辨率的特征由一个独立的输入(称为风格向量)来控制,从而操纵生成图像的风格,以及如何通过将图像之间的风格进行交换来操作不同图像的风格。

盼小辉丶的博客 7645

【WorkBuddy专栏36】从踩坑到上线——WorkBuddy代码开发避坑指南与部署完全手册

【WorkBuddy专栏36】从踩坑到上线——WorkBuddy代码开发避坑指南与部署完全手册

AI人人懂 1074

OV9734 DATASHEET,完整规格书

OV9734完整规格书,包括电气参数,尺寸规格,寄存器配置表等

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。

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")

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。

上一篇: Do Large Language Models Know How Much They Know?
下一篇: Emergent Symbolic Mechanisms Support Abstract Reasoning in 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