{"list":"other","total":58,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2406.11409","title":"CodeGemma: Open Code Models Based on Gemma","created":"2024-06-17","cited_by_count":150},{"id":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149},{"id":"1806.09029","title":"Improving Text-to-SQL Evaluation Methodology","created":"2018-06-23","cited_by_count":135},{"id":"2101.06983","title":"Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup","created":"2021-01-18","cited_by_count":127},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125},{"id":"1304.6480","title":"A Theoretical Analysis of NDCG Type Ranking Measures","created":"2013-04-24","cited_by_count":119},{"id":"2305.02437","title":"Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory","created":"2023-05-03","cited_by_count":103},{"id":"2406.14497","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","created":"2024-06-20","cited_by_count":91},{"id":"2006.05405","title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","created":"2020-06-09","cited_by_count":89},{"id":"2407.15831","title":"NV-Retriever: Improving text embedding models with effective hard-negative mining","created":"2024-07-22","cited_by_count":84},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73},{"id":"2304.10778","title":"Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT","created":"2023-04-21","cited_by_count":71},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47},{"id":"2309.14534","title":"Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education","created":"2023-09-25","cited_by_count":39},{"id":"2110.15439","title":"Dense Hierarchical Retrieval for Open-Domain Question Answering","created":"2021-10-28","cited_by_count":34},{"id":"2402.01935","title":"Code Representation Learning At Scale","created":"2024-02-02","cited_by_count":26},{"id":"2409.09916","title":"SFR-RAG: Towards Contextually Faithful LLMs","created":"2024-09-16","cited_by_count":19},{"id":"2410.07739","title":"SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture","created":"2024-10-10","cited_by_count":19},{"id":"2206.07245","title":"An Extractive-and-Abstractive Framework for Source Code Summarization","created":"2022-06-15","cited_by_count":18},{"id":"2405.18069","title":"An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates","created":"2024-05-28","cited_by_count":6},{"id":"2401.09885","title":"Source Code Clone Detection Using Unsupervised Similarity Measures","created":"2024-01-18","cited_by_count":5},{"id":"2403.09740","title":"Teaching Machines to Code: Smart Contract Translation with LLMs","created":"2024-03-13","cited_by_count":3},{"id":"2409.05824","title":"Are Large Language Models a Threat to Programming Platforms? An Exploratory Study","created":"2024-09-09","cited_by_count":3}],"next_cursor":null}