From 7a5d9f37b73388f7143aec3ef4f398e0854ca3aa Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Thu, 4 Jul 2024 01:10:05 +0900 Subject: [PATCH 1/7] Add Using Towards Automating Code Review Activities Paper --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 7a22df9..b31aa0e 100644 --- a/README.md +++ b/README.md @@ -694,6 +694,7 @@ Please feel free to send a pull request to add papers and relevant content that - **AUGER: Automatically Generating Review Comments with Pre-training Models** (2022), FSE'22, Li, Lingwei, et al. [[pdf]](https://arxiv.org/pdf/2208.08014) - **Automating Code Review Activities by Large-Scale Pre-training** (2022), FSE'22, Li, Zhiyu, et al. [[pdf]](https://arxiv.org/pdf/2203.09095) - **Using Pre-Trained Models to Boost Code Review Automation** (2022), ICSE'22, Tufano, et al. [[pdf]](https://arxiv.org/abs/2201.06850) +- **Using Towards Automating Code Review Activities** (2021), ICSE'21, Tufano, et al. [[pdf]](https://arxiv.org/pdf/2101.02518) ## Code Documentation From 4d85e750338f5f74cbc7622a8f4160323a21ac0f Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Thu, 4 Jul 2024 01:13:37 +0900 Subject: [PATCH 2/7] Add CodeReviewer Code --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b31aa0e..50b4aa5 100644 --- a/README.md +++ b/README.md @@ -692,7 +692,7 @@ Please feel free to send a pull request to add papers and relevant content that - **Generation-based Code Review Automation: How Far Are We?** (2023), arxiv, Zhou, Xin, et al. [[pdf]](https://arxiv.org/pdf/2303.07221) - **D-ACT: Towards Diff-Aware Code Transformation for Code Review Under a Time-Wise Evaluation** (2023), arxiv, Pornprasit, Chanathip, et al. [[pdf]](https://www.researchgate.net/profile/Chakkrit-Tantithamthavorn/publication/367075263_D-ACT_Towards_Diff-Aware_Code_Transformation_for_Code_Review_Under_a_Time-Wise_Evaluation/links/63c03c9556d41566df5e52f2/D-ACT-Towards-Diff-Aware-Code-Transformation-for-Code-Review-Under-a-Time-Wise-Evaluation.pdf) - **AUGER: Automatically Generating Review Comments with Pre-training Models** (2022), FSE'22, Li, Lingwei, et al. [[pdf]](https://arxiv.org/pdf/2208.08014) -- **Automating Code Review Activities by Large-Scale Pre-training** (2022), FSE'22, Li, Zhiyu, et al. [[pdf]](https://arxiv.org/pdf/2203.09095) +- **Automating Code Review Activities by Large-Scale Pre-training** (2022), FSE'22, Li, Zhiyu, et al. [[pdf]](https://arxiv.org/pdf/2203.09095) [[code]](https://github.com/microsoft/CodeBERT/tree/master/CodeReviewer) - **Using Pre-Trained Models to Boost Code Review Automation** (2022), ICSE'22, Tufano, et al. [[pdf]](https://arxiv.org/abs/2201.06850) - **Using Towards Automating Code Review Activities** (2021), ICSE'21, Tufano, et al. [[pdf]](https://arxiv.org/pdf/2101.02518) From d04b64a3b29d6cf20e5958f4f4021cada93d6e50 Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Thu, 4 Jul 2024 01:17:22 +0900 Subject: [PATCH 3/7] Add Improving Automated Code Reviews: Learning from Experience** (2024), MSR'24 --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 50b4aa5..750c4e4 100644 --- a/README.md +++ b/README.md @@ -680,6 +680,7 @@ Please feel free to send a pull request to add papers and relevant content that ## Code Review +- **Improving Automated Code Reviews: Learning from Experience** (2024), MSR'24, Hong Yi Lin et al. [[pdf]](https://arxiv.org/abs/2402.03777) - **Security Code Review by LLMs: A Deep Dive into Responses** (2024), arxiv, Yu et al. [[pdf]](https://arxiv.org/pdf/2401.16310) - **GPT-3.5 for Code Review Automation: How Do Few-Shot Learning, Prompt Design, and Model Fine-Tuning Impact Their Performance?** (2024), arxiv, Pornprasit, C., & Tantithamthavorn, C. [[pdf]](https://arxiv.org/pdf/2402.00905) - **Resolving Code Review Comments with Machine Learning** (2023), ICSE'24, Frömmgen, et al. [[pdf]](https://storage.googleapis.com/gweb-research2023-media/pubtools/pdf/0449374e831a796a5e88f92380c64e7e090c6dfa.pdf) From 232ab3955db5482d85bc09a7d5c0a2260af988db Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Thu, 4 Jul 2024 01:24:58 +0900 Subject: [PATCH 4/7] update conf --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 750c4e4..76208d0 100644 --- a/README.md +++ b/README.md @@ -685,7 +685,7 @@ Please feel free to send a pull request to add papers and relevant content that - **GPT-3.5 for Code Review Automation: How Do Few-Shot Learning, Prompt Design, and Model Fine-Tuning Impact Their Performance?** (2024), arxiv, Pornprasit, C., & Tantithamthavorn, C. [[pdf]](https://arxiv.org/pdf/2402.00905) - **Resolving Code Review Comments with Machine Learning** (2023), ICSE'24, Frömmgen, et al. [[pdf]](https://storage.googleapis.com/gweb-research2023-media/pubtools/pdf/0449374e831a796a5e88f92380c64e7e090c6dfa.pdf) - **Team-related Features in Code Review Prediction Models** (2023), arxiv, Witter, Eduardo et al. [[pdf]](https://arxiv.org/pdf/2312.06244) -- **Unity is Strength: Cross-Task Knowledge Distillation to Improve Code Review Generation** (2023), arxiv, Sghaier et al. [[pdf]](https://arxiv.org/pdf/2309.03362) +- **Unity is Strength: Cross-Task Knowledge Distillation to Improve Code Review Generation** (2023), ISSRE'23, Sghaier et al. [[pdf]](https://arxiv.org/pdf/2309.03362) - **LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning** (2023), arxiv, Lu, Junyi, et al. [[pdf]](https://arxiv.org/pdf/2308.11148) - **Learning to Predict Code Review Completion Time In Modern Code Review** (2023), EMSE journal, Chouchen, Moataz, et al. - **ReviewRanker: A Semi-Supervised Learning Based Approach for Code Review Quality Estimation** (2023), arxiv, Mahbub, Saifullah, et al. [[pdf]](https://arxiv.org/pdf/2307.03996) From c76b529ff19db821efd7b34ea74395b5f6cb7c3b Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Thu, 4 Jul 2024 01:28:24 +0900 Subject: [PATCH 5/7] revert conf and update ISSRE'23 --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 76208d0..3220bbe 100644 --- a/README.md +++ b/README.md @@ -685,8 +685,8 @@ Please feel free to send a pull request to add papers and relevant content that - **GPT-3.5 for Code Review Automation: How Do Few-Shot Learning, Prompt Design, and Model Fine-Tuning Impact Their Performance?** (2024), arxiv, Pornprasit, C., & Tantithamthavorn, C. [[pdf]](https://arxiv.org/pdf/2402.00905) - **Resolving Code Review Comments with Machine Learning** (2023), ICSE'24, Frömmgen, et al. [[pdf]](https://storage.googleapis.com/gweb-research2023-media/pubtools/pdf/0449374e831a796a5e88f92380c64e7e090c6dfa.pdf) - **Team-related Features in Code Review Prediction Models** (2023), arxiv, Witter, Eduardo et al. [[pdf]](https://arxiv.org/pdf/2312.06244) -- **Unity is Strength: Cross-Task Knowledge Distillation to Improve Code Review Generation** (2023), ISSRE'23, Sghaier et al. [[pdf]](https://arxiv.org/pdf/2309.03362) -- **LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning** (2023), arxiv, Lu, Junyi, et al. [[pdf]](https://arxiv.org/pdf/2308.11148) +- **Unity is Strength: Cross-Task Knowledge Distillation to Improve Code Review Generation** (2023), arxiv, Sghaier et al. [[pdf]](https://arxiv.org/pdf/2309.03362) +- **LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning** (2023), ISSRE'23, Lu, Junyi, et al. [[pdf]](https://arxiv.org/pdf/2308.11148) - **Learning to Predict Code Review Completion Time In Modern Code Review** (2023), EMSE journal, Chouchen, Moataz, et al. - **ReviewRanker: A Semi-Supervised Learning Based Approach for Code Review Quality Estimation** (2023), arxiv, Mahbub, Saifullah, et al. [[pdf]](https://arxiv.org/pdf/2307.03996) - **ToxiSpanSE: An Explainable Toxicity Detection in Code Review Comments** (2023), arxiv, Saker, Jaydeb, et al. [[pdf]](https://arxiv.org/pdf/2307.03386) From 8821fc6ffb944b852295b23b24c576610d3fee7d Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Mon, 8 Jul 2024 15:00:18 +0900 Subject: [PATCH 6/7] change order --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3220bbe..57f14bd 100644 --- a/README.md +++ b/README.md @@ -681,8 +681,8 @@ Please feel free to send a pull request to add papers and relevant content that ## Code Review - **Improving Automated Code Reviews: Learning from Experience** (2024), MSR'24, Hong Yi Lin et al. [[pdf]](https://arxiv.org/abs/2402.03777) -- **Security Code Review by LLMs: A Deep Dive into Responses** (2024), arxiv, Yu et al. [[pdf]](https://arxiv.org/pdf/2401.16310) - **GPT-3.5 for Code Review Automation: How Do Few-Shot Learning, Prompt Design, and Model Fine-Tuning Impact Their Performance?** (2024), arxiv, Pornprasit, C., & Tantithamthavorn, C. [[pdf]](https://arxiv.org/pdf/2402.00905) +- **Security Code Review by LLMs: A Deep Dive into Responses** (2024), arxiv, Yu et al. [[pdf]](https://arxiv.org/pdf/2401.16310) - **Resolving Code Review Comments with Machine Learning** (2023), ICSE'24, Frömmgen, et al. [[pdf]](https://storage.googleapis.com/gweb-research2023-media/pubtools/pdf/0449374e831a796a5e88f92380c64e7e090c6dfa.pdf) - **Team-related Features in Code Review Prediction Models** (2023), arxiv, Witter, Eduardo et al. [[pdf]](https://arxiv.org/pdf/2312.06244) - **Unity is Strength: Cross-Task Knowledge Distillation to Improve Code Review Generation** (2023), arxiv, Sghaier et al. [[pdf]](https://arxiv.org/pdf/2309.03362) From cdaae93bb6bdd52c86e2d952a5810c4fbeb2b0f1 Mon Sep 17 00:00:00 2001 From: Yonghwi Kwon Date: Mon, 8 Jul 2024 15:04:50 +0900 Subject: [PATCH 7/7] Add TSE`24 Journals : Code Review Automation: Strengths and Weaknesses of the State of the Art --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 57f14bd..4dfb164 100644 --- a/README.md +++ b/README.md @@ -680,6 +680,7 @@ Please feel free to send a pull request to add papers and relevant content that ## Code Review +- **Code Review Automation: Strengths and Weaknesses of the State of the Art** (2024), TSE'24, Tufano, et al. - **Improving Automated Code Reviews: Learning from Experience** (2024), MSR'24, Hong Yi Lin et al. [[pdf]](https://arxiv.org/abs/2402.03777) - **GPT-3.5 for Code Review Automation: How Do Few-Shot Learning, Prompt Design, and Model Fine-Tuning Impact Their Performance?** (2024), arxiv, Pornprasit, C., & Tantithamthavorn, C. [[pdf]](https://arxiv.org/pdf/2402.00905) - **Security Code Review by LLMs: A Deep Dive into Responses** (2024), arxiv, Yu et al. [[pdf]](https://arxiv.org/pdf/2401.16310)