{"id":28098963,"url":"https://github.com/thu-keg/vta","last_synced_at":"2026-02-16T07:02:11.418Z","repository":{"id":113496271,"uuid":"596817574","full_name":"THU-KEG/VTA","owner":"THU-KEG","description":"Code, APIs and data for the CIKM23 paper \"LittleMu: Deploying an Online Virtual Teaching Assistant via Heterogeneous Sources Integration and Chain-of-Teach Prompts\"","archived":false,"fork":false,"pushed_at":"2023-02-08T03:17:55.000Z","size":1725,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-10-09T20:38:42.599Z","etag":null,"topics":["dialogue-system","education","mooc"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2308.05935","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/THU-KEG.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-02-03T01:34:38.000Z","updated_at":"2023-08-15T13:13:08.000Z","dependencies_parsed_at":null,"dependency_job_id":"a29e3f3c-0998-4739-9434-9ede7b53b2cd","html_url":"https://github.com/THU-KEG/VTA","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/THU-KEG/VTA","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THU-KEG%2FVTA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THU-KEG%2FVTA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THU-KEG%2FVTA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THU-KEG%2FVTA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/THU-KEG","download_url":"https://codeload.github.com/THU-KEG/VTA/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/THU-KEG%2FVTA/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29502929,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-16T05:57:17.024Z","status":"ssl_error","status_checked_at":"2026-02-16T05:56:49.929Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dialogue-system","education","mooc"],"created_at":"2025-05-13T17:59:18.153Z","updated_at":"2026-02-16T07:02:11.401Z","avatar_url":"https://github.com/THU-KEG.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# VTA (Virtual Teaching Assistant)\nData and code for LittleMu: Deploying an Online Virtual Teaching Assistant via Heterogeneous Sources Integration and Chain-of-Teach Prompts.\n\n# Data\n\nTo facilitate the development and evaluation for future VTA systems, we present the **VTA** dataset, which consists of 3 kinds of data: \n\n- human preference scores for different models\n-  coarse-to-fine intention for history dialogues \n- reference answers for real questions. \n\n| Task                     | Courses | Participants | Label   |\n| ------------------------ | ------- | ------------ | ------- |\n| Intention Classification | 139     | 10           | 4,000   |\n| Question Answering       | 139     | 10           | 1,767   |\n| General Dialog           | 20      | 20           | 124,512 |\n\nYou can download the VTA dataset at  [this repository](https://github.com/THU-KEG/VTA/tree/main/VTA_dataset) \n\n- The data access permission is granted by XuetangX. We follow the privacy policy and protect the users' data by deploying our system on the company's intranet to prevent data leaking. Therefore, we  anonymize the user's name for the intention and QA data using real history dialogues. \n- See more details in our [README](https://github.com/THU-KEG/VTA/tree/main/VTA_dataset) for VTA dataset\n\nHere we share the collection process for VTA dataset:\n\n- Intention Classification dataset's  [annotation guideline](https://kvbpkpddff.feishu.cn/docx/LsSkdZwOEoIBZCxeU0Wc414qnLd)\n- Question Answering dataset's [annotation guideline](https://kvbpkpddff.feishu.cn/docx/EOsJdZbIdoWrcqx0MwCcYRdtnHb)\n- General Dialog dataset's [annotation guideline](https://kvbpkpddff.feishu.cn/docx/doxcn3OhKgFU0zPxDT0yiszULQh)\n\n\n\n# Code\n\nFor more deployment details, you can view this [document](https://kvbpkpddff.feishu.cn/docx/doxcnCgjYpEK0ms7KCrEmBx2Iuc)\n\n- The retrieval module is implemented in this [repository](http://xiaomu-student.xuetangx.com/gitlab/xuwei/xiaomu)\n  - As the retrieval module utilized course-specific data on XuetangX MOOC platform, we will check the privacy policy and release the visible database in next a few weeks.\n\n- The generation module is  implemented in this [repository](https://github.com/lcy2723/XDAI)\n  - The  generation module is implemented based on some code from [XDAI](https://github.com/THUDM/XDAI)\n\n# Milestones\n\nWe record our discussions, progresses and weekly plans in this [document](https://kvbpkpddff.feishu.cn/docx/doxcnbT70XKGLC1uTV19243bY0e)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthu-keg%2Fvta","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthu-keg%2Fvta","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthu-keg%2Fvta/lists"}