bakaEC/OliveSensorAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
000491f1be
OliveSensorAPI/evaluate/Professional_evaluation.md
Anooyman 000491f1be
Merge Main code (#2) 
* Add files via upload

* 新增ENmd文档

* Update README.md

* Update README_EN.md

* Update LICENSE

* [docs] update lmdeploy file

* add ocr.md

* Update tutorial.md

* Update tutorial_EN.md

* Update General_evaluation_EN.md

* Update General_evaluation_EN.md

* Update README.md

Add InternLM2_7B_chat_full's professional evaluation results

* Update Professional_evaluation.md

* Update Professional_evaluation.md

* Update Professional_evaluation.md

* Update Professional_evaluation.md

* Update Professional_evaluation_EN.md

* Update README.md

* Update README.md

* Update README_EN.md

* Update README_EN.md

* Update README_EN.md

* [DOC] update readme

* Update LICENSE

* Update LICENSE

* update personal info and small format optimizations

* update personal info and translations for contents in a table

* Update RAG README

* Update demo link in README.md

* Update xlab app link

* Update xlab link

* add xlab model

* Update web_demo-aiwei.py

* add bitex

---------

Co-authored-by: xzw <62385492+aJupyter@users.noreply.github.com>
Co-authored-by: এ許我辞忧࿐♡ <127636623+Smiling-Weeping-zhr@users.noreply.github.com>
Co-authored-by: Vicky <vicky_3021@163.com>
Co-authored-by: MING_X <119648793+MING-ZCH@users.noreply.github.com>
Co-authored-by: Nobody-ML <1755309985@qq.com>
Co-authored-by: 8baby8 <3345710651@qq.com>
Co-authored-by: chaoke <101492509+8baby8@users.noreply.github.com>
Co-authored-by: aJupyter <ajupyter@163.com>
Co-authored-by: HongCheng <kwchenghong@gmail.com>
Co-authored-by: santiagoTOP <“1537211712top@gmail.com”>
2024-03-15 19:51:04 +08:00

1.6 KiB
Raw Blame History

EmoLLM专业指标评估

简介

本文档介绍一种专业评测方法，并提供 EmoLLM 在专业指标的得分。

评测方法

本评测方法采用论文《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》提出的评测指标与方法。

  • 指标：Comprehensiveness, Professionalism, Authenticity, Safety
  • 方法：Turn-Based Dialogue Evaluation
  • 数据集：CPsyCounE

评测结果

Model Comprehensiveness Professionalism Authenticity Safety
InternLM2_7B_chat_qlora 1.32 2.20 2.10 1.00
InternLM2_7B_chat_full 1.40 2.45 2.24 1.00

比较

  • EmoLLM V2.0 相比 EmoLLM V1.0 在指标上全面提升！已超越 Role-playing ChatGPT 在心理咨询任务上的能力！

  • EmoLLM V1.0 在 InternLM2_7B_Chat 基础上提升较大；相比 Role-playing ChatGPT 在心理咨询任务上能力相近

  • 对比结果图片来源于论文《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》 image