★★★★★
- wikipedia相关知识内容, 由给定prompt问题和五个选项，预测正确答案
- 关键在于RAG优化, 主流包括采用LLM做或者deberta分类来做
- 标题和第一句话来召回文章articles，再从文章中召回相关句子
- 或直接召回整个段落, (separated by '\n')
- 1st inference code discussion
- 3rd rerank code discussion
- 6th code discussion
- 12nd discussion-zhihu
- example: Elastic search in kaggle
- kaggle LLM science大模型比赛金牌方案总结 - 包包大人的文章 - 知乎
- kaggle大模型竞赛优胜方案总结与思考 - hxshine的文章 - 知乎
kaggle-LLM-Detect AI Generated Text
★★★★☆
- 1st code
**LMSYS - Chatbot Arena Human Preference Predictions
- 1st code
- 2nd code
- 3rd discussion
WSDM 2024 Conversational Multi-Doc QA
- 1st code
KDD-Meta_RAG
KDD-Amazon
kaggle-AI Mathematical Olympiad
- 1st infer code
- 2nd code discussion
- 3rd infer code discussion
★★★★★
- 包含pdf解析、SQL生成、意图识别、RAG召回、prompt问答
★★★☆☆
- PDF解析, RAG, LLM prompt问答
- 4th code
- 6th discussion
- 13rd code
ATEC2023-科技精英赛—大模型的知识引入
- 7th code
- 2nd code
CCF AIOps 2024
- 1st discussion
- 2nd code
Feedback Prize - English Language Learning
- 1st code discussion
- 3rd code discussion
- 13rd code
kaggle-CommonLit Readability Prize
- 1st code discussion
- 2nd code discussion
- 3rd code discussion
- 4th code discussion
- 5th discussion
- 6th discussion
- 9th discussion
- 12th discussion
- 13th discussion
- 14th discussion
- 15th discussion
- 16th discussion
- 18th discussion
- 20th code discussion
- 22nd discussion
- 24th discussion
- 25th. discussion
- 28th. discussion
- 37th. discussion
- 40th. discussion
- 47th. discussion
- 48th. discussion
- 69th. discussion
- 87th. discussion
- 100th. discussion
- code
kaggle2022-Jigsaw Rate Severity of Toxic Comments
- 1st code
- 14th code discussion
kaggle2020-Jigsaw Multilingual Toxic Comment Classification
- 1st discussion post-processing
- 3rd code discussion
- 4th discussion
- 6th discussion
- 10th discussion
kaggle2019-Jigsaw Unintended Bias in Toxicity Classification
kaggle2018-Toxic Comment Classification Challenge
kaggle-Google QUEST Q&A Labeling
- 1st code discussion
★★★★★
- 1st code discussion
- 2nd code discussion
- 3rd code discussion
- 4th code discussion
- 5th code discussion
- 9th code discussion
- 11st code discussion
人工智能技术创新大赛——商品标题实体识别
达观杯
kaggle-U.S. Patent Phrase to Phrase Matching
- 1st code discussion
- 2nd discussion
- 3rd discussion
- 5th discussion
- 7th discussion
- 8th discussion
- 10th discussion
- 12th discussion
- 24th discussion
- 31st code discussion
- 41st discussion
- Kaggle 专利匹配比赛金牌方案赛后总结 - 致Great的文章 - 知乎
kaggle-TensorFlow 2.0 Question Answering
- 7st code
- collection dicsussion
- 1st code discussion
- 24th code
- unk code
- 1st code
- 4th code
- 6th code discussion
- 8th code
- 1st code discussion
- 4th code
- 128th code
- 1st code
- 2nd code
kaggle-Learning Equality - Curriculum Recommendations
★★★★★
- 多语言content与topic的文本匹配问题
- 召回：tfidf + transformer arcface + rule
- 排序：LGB
- 1st code discussion
- 2nd code discussion
- 3rd code discussion
- 4th code discussion
- 5th discussion
- 6th discussion
- 7th discussion
- 9th discussion
- 10th discussion
- 12nd discussion
- 15th discussion
- 26th discussion
★★★☆☆
- 电商场景下，中文匹配. 开源较少
- 2nd code discussion
- 13rd code
★★★★☆
★★★★★
- notebook根据code cell 顺序markdown cell顺序
WSDM2023 Pre-training for Web Search
- 1st code
- 1st code
- 多fold来分别做这件事。多步迭代选择困难负样本，最终选择Top20. 初始向量模型召回1000/200，200作为困难负样本微调向量模型召回100，召回100的部分作为排序负样本，最终选择20
- 3rd code
- code
- 7th code
- 8th code
- 9th code
- code
kaggle-Tweet Sentiment Extraction
- 1st code discussion
- 2nd discussion
- 7th code
- base code code
- 12nd code discussion
**CCKS&百度 2019中文短文本的实体链指))
https://github.com/luhua-rain/MRC_Competition_Dureader
- 1st code
- 4th code
- 5th discussion
- 36th discussion
- 2nd discussion