{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"OlympicArena","owner":"GAIR-NLP","isFork":false,"description":"This is the official repository of the paper \"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI\"","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":71,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-27T15:07:15.567Z"}},{"type":"Public","name":"Safety-J","owner":"GAIR-NLP","isFork":false,"description":"Safety-J: Evaluating Safety with Critique","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":9,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-25T08:13:26.911Z"}},{"type":"Public","name":"factool","owner":"GAIR-NLP","isFork":false,"description":"FacTool: Factuality Detection in Generative AI","allTopics":["python","natural-language-processing","fact-checking","large-language-models","generative-ai","chatgpt"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":19,"starsCount":788,"forksCount":61,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-19T08:32:56.972Z"}},{"type":"Public","name":"MoPS","owner":"GAIR-NLP","isFork":false,"description":"[ACL 2024] Code for \"MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation\"","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":22,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-19T07:39:20.796Z"}},{"type":"Public","name":"weak-to-strong-reasoning","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":26,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-19T02:20:53.044Z"}},{"type":"Public","name":"anole","owner":"GAIR-NLP","isFork":false,"description":"Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":18,"starsCount":547,"forksCount":29,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-15T08:09:55.408Z"}},{"type":"Public","name":"self-improvement-reversal","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":8,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-14T16:33:16.519Z"}},{"type":"Public","name":"BeHonest","owner":"GAIR-NLP","isFork":false,"description":"BeHonest: Benchmarking Honesty in Large Language Models","allTopics":["nlp","benchmark","evaluation","alignment","honesty","llm"],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":23,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-09T06:55:57.801Z"}},{"type":"Public","name":"MathPile","owner":"GAIR-NLP","isFork":false,"description":"Generative AI for Math: MathPile","allTopics":["math","corpus","language-model","pre-training","large-language-models"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":364,"forksCount":19,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-23T11:07:05.520Z"}},{"type":"Public","name":"MetaCritique","owner":"GAIR-NLP","isFork":false,"description":"Evaluate the Quality of Critique","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":32,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-01T17:57:45.089Z"}},{"type":"Public","name":"alignment-for-honesty","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":61,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-22T06:23:43.712Z"}},{"type":"Public","name":"benbench","owner":"GAIR-NLP","isFork":false,"description":"Benchmarking Benchmark Leakage in Large Language Models","allTopics":["dataset","benchmarks","leakage-detection","large-language-models"],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":3,"starsCount":36,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-20T01:59:32.735Z"}},{"type":"Public","name":"Preference-Dissection","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":20,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T07:56:58.115Z"}},{"type":"Public","name":"cs2916","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":19,"forksCount":8,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-12T07:37:35.074Z"}},{"type":"Public","name":"ReAlign","owner":"GAIR-NLP","isFork":false,"description":"Reformatted Alignment","allTopics":["nlp","natural-language-processing","alignment","large-language-models","llms","generative-ai"],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":97,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-22T14:41:27.114Z"}},{"type":"Public","name":"ReasonEval","owner":"GAIR-NLP","isFork":false,"description":"Evaluating Mathematical Reasoning Beyond Accuracy","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":30,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-09T09:21:30.572Z"}},{"type":"Public","name":"OPO","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":49,"forksCount":6,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-02T15:01:34.594Z"}},{"type":"Public","name":"scaleeval","owner":"GAIR-NLP","isFork":false,"description":"Scalable Meta-Evaluation of LLMs as Evaluators","allTopics":["nlp","evaluation-framework","llm","generative-ai"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":36,"forksCount":3,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-15T13:54:40.105Z"}},{"type":"Public","name":"SimulateBench","owner":"GAIR-NLP","isFork":false,"description":"GPT as Human","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":17,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-21T09:20:34.788Z"}},{"type":"Public","name":"Entropy-ABF","owner":"GAIR-NLP","isFork":false,"description":"Official implementation for 'Extending LLMs’ Context Window with 100 Samples'","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":72,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-18T02:37:21.956Z"}},{"type":"Public","name":"auto-j","owner":"GAIR-NLP","isFork":false,"description":"Generative Judge for Evaluating Alignment","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":193,"forksCount":10,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-18T02:37:17.655Z"}},{"type":"Public","name":"abel","owner":"GAIR-NLP","isFork":false,"description":"SOTA Math Opensource LLM","allTopics":["math","llm","generative-ai"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":10,"starsCount":290,"forksCount":17,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-12T14:01:05.446Z"}},{"type":"Public","name":"ChineseFactEval","owner":"GAIR-NLP","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-09-13T10:27:52.810Z"}}],"repositoryCount":23,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"GAIR-NLP repositories"}