Stream of Revision adds action tokens to LLM decoding so the model can revise its own code history on the fly, cutting vulnerabilities in generated code with little added cost.
Feldman, Arjun Guha, Michael Greenberg, and Abhinav Jangda
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Parallel-SFT mixes parallel programs across languages during SFT to produce more transferable RL initializations, yielding better zero-shot generalization to unseen programming languages.
A distribution-free abstention rule grounded in multiple hypothesis testing uses execution consistency to let code LLMs avoid hallucination-prone tasks with theoretical guarantees.
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
citing papers explorer
-
Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
Stream of Revision adds action tokens to LLM decoding so the model can revise its own code history on the fly, cutting vulnerabilities in generated code with little added cost.
-
Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL
Parallel-SFT mixes parallel programs across languages during SFT to produce more transferable RL initializations, yielding better zero-shot generalization to unseen programming languages.
-
Task Abstention for Large Language Models in Code Generation
A distribution-free abstention rule grounded in multiple hypothesis testing uses execution consistency to let code LLMs avoid hallucination-prone tasks with theoretical guarantees.
-
StarCoder 2 and The Stack v2: The Next Generation
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
-
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
-
StarCoder: may the source be with you!
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
- Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild