This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
| karl [2025/04/23 15:02] sergio | karl [2025/08/18 08:59] (current) sergio | ||
|---|---|---|---|
| Line 9: | Line 9: | ||
| This project will consist of two different workflows or tasks, see below: \\ | This project will consist of two different workflows or tasks, see below: \\ | ||
| + | |||
| + | * **[[https://nm.oho2.com/s/T7NCcKqMpmmbXc3|Centific - Karl - 3P Prompt Rewrite 2]]**\\ | ||
| + | * **[[https://nm.oho2.com/s/gdXKPwBBrFcMTkN|JSON content instruction]]**\\ | ||
| + | * **[[https://nm.oho2.com/s/NyfMZKpgacNwM9g|Uber_Project_Karl]]**\\ | ||
| + | |||
| + | |||
| + | |||
| **Quality Grading Task (SxS)**: In this workflow, we will evaluate translation quality automatically generated. Your task will be to choose from a range of 0 to 6 the quality level for each of the translations that appear as options based on 2 error categories: accuracy and fluency. \\ | **Quality Grading Task (SxS)**: In this workflow, we will evaluate translation quality automatically generated. Your task will be to choose from a range of 0 to 6 the quality level for each of the translations that appear as options based on 2 error categories: accuracy and fluency. \\ | ||
| Line 37: | Line 44: | ||
| * [[https://nm.oho2.com/s/CXc794PWBjyGmFE|Overview of the tool & important guidelines to keep in mind]]\\ | * [[https://nm.oho2.com/s/CXc794PWBjyGmFE|Overview of the tool & important guidelines to keep in mind]]\\ | ||
| - | * [[https://nm.oho2.com/s/MJtRq3iL9zEzcks|Guidelines_ i18n S_S Eval Type 2]].\\ | + | * [[https://nm.oho2.com/s/Yfzr5mHTpYSHdsD|Guidelines_ i18n S_S Eval Type 2]].\\ | 
| **LLM Grounding Factuality Task**: In this task, you are asked to assess the truthfulness or factuality by choosing the correct level of accuracy contained in the Responses. For this, you will need to identify each claim that make up the response. \\ | **LLM Grounding Factuality Task**: In this task, you are asked to assess the truthfulness or factuality by choosing the correct level of accuracy contained in the Responses. For this, you will need to identify each claim that make up the response. \\ | ||
| Line 123: | Line 130: | ||
| * [[https://nm.oho2.com/s/k9ZJCNnJymkzqsK|Cultural Relevance Benchmarking Rubric - Phase 2 - HI]]\\ | * [[https://nm.oho2.com/s/k9ZJCNnJymkzqsK|Cultural Relevance Benchmarking Rubric - Phase 2 - HI]]\\ | ||
| * [[https://nm.oho2.com/s/zndfMtXxN7cQoQH|Training India Cultural Evals]]\\ | * [[https://nm.oho2.com/s/zndfMtXxN7cQoQH|Training India Cultural Evals]]\\ | ||
| + | * [[https://nm.oho2.com/s/MienH725rfagXdN|Rating Criteria Detailed Explanation]]\\ | ||
| Line 160: | Line 168: | ||
| + | **Rubric Review** | ||
| + | The goal of this task is to review each individual rubric property for a prompt. Assume you are a teacher responsible for scoring student responses and validate, correct, or remove the given rubrics.\\ | ||
| + | More detailed guidelines are here:\\ | ||
| - | + | * [[https://nm.oho2.com/s/jjs2Y4H6pWNN4xZ|Rubric Review]]\\ | |
| - | * **[[https://nm.oho2.com/s/T7NCcKqMpmmbXc3|CrC Translation Instructions]]**\\ | + | * [[https://nm.oho2.com/s/xAE9cXQ5oWdqnRH|Guidelines for Rubric Review]]\\ | 
| - | * **[[https://nm.oho2.com/s/T7NCcKqMpmmbXc3|Centific - Karl - 3P Prompt Rewrite 2]]**\\ | + | * [[https://nm.oho2.com/s/eLNRSBxKPkfKfyR|Rubric Review Training]]\\ | 
| - | * **[[https://nm.oho2.com/s/tjHHW8HALpLj2B9|i18N Question Data Post-editing Instruction]]**\\ | + | * [[https://nm.oho2.com/s/9nZDE5tigkBddNq|RUBRIC REVIEW - DO’S AND DON'TS]] | 
| - | * **[[https://nm.oho2.com/s/gdXKPwBBrFcMTkN|JSON content instruction]]**\\ | + | |
| - | * **[[https://nm.oho2.com/s/R8B8BNXtqQpJfKs|Karl_Human Translation and Review Guideline.v.1 ]]**\\ | + | |
| - | * **[[https://nm.oho2.com/s/68ifaJZXoGEit46|Training session for Karl_Loc_Project]]**\\ | + | |
| - | * **[[https://nm.oho2.com/s/387MbnizT6pgLCy|Translation AI Style guide for Human Evaluations ]]**\\ | + | |
| - | * **[[https://nm.oho2.com/s/NyfMZKpgacNwM9g|Uber_Project_Karl]]**\\ | + | |