REVIEW 8 cited by
Conversational Automated Program Repair
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Automated Program Repair (APR) can help developers automatically generate patches for bugs. Due to the impressive performance obtained using Large Pre-Trained Language Models (LLMs) on many code related tasks, researchers have started to directly use LLMs for APR. However, prior approaches simply repeatedly sample the LLM given the same constructed input/prompt created from the original buggy code, which not only leads to generating the same incorrect patches repeatedly but also miss the critical information in testcases. To address these limitations, we propose conversational APR, a new paradigm for program repair that alternates between patch generation and validation in a conversational manner. In conversational APR, we iteratively build the input to the model by combining previously generated patches with validation feedback. As such, we leverage the long-term context window of LLMs to not only avoid generating previously incorrect patches but also incorporate validation feedback to help the model understand the semantic meaning of the program under test. We evaluate 10 different LLM including the newly developed ChatGPT model to demonstrate the improvement of conversational APR over the prior LLM for APR approach.
Forward citations
Cited by 8 Pith papers
-
AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation
AssumptionMiner extracts implicit assumptions from LLM-generated code with a cross-model ensemble F1 of 0.816 on a new 180-task benchmark, and enables assumption-guided targeted regeneration.
-
Prefactory: Automated Discovery and Application of Library-Adoption Refactorings
Prefactory uses LLM-generated lexical and structural detectors to find and validate library-adoption refactorings in Python, detecting 75 of 100 benchmark instances and producing 40 test-validated rewrites.
-
Towards Automated Formal Verification of zkEVMs Using LLM-Guided Constraint Synthesis
VeriSynth synthesizes executable Z3 verification models from zkEVM Rust source via LLM-guided translation with solver-backed checking, detecting 91.6% of 95 injected opcode bugs versus 46.3% for a direct LLM baseline ...
-
IFEvalCode: Controlled Code Generation
A 1,620-sample, 8-language, Chinese/English benchmark separates code correctness from instruction-following and shows instruction compliance is far lower than correctness across 40+ LLMs.
-
Knowledge-Enhanced Program Repair for Data Science Code
DSrepair combines a knowledge graph of data science APIs with AST-level bug localization to repair LLM-generated code, fixing more DS-1000 tasks than five baseline repair methods.
-
Automated Repair of C Programs Using Large Language Models
An agent that combines spectrum-based fault localization, test feedback, and chain-of-thought prompting repairs 44.93% of 3,902 Codeflaws C bugs, a 3.61-point gain over GPT-4 with CoT.
-
$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models
A staged tree-of-thought framework called T3 raises LLM-based automated program repair success rates by about 10 to 12 percentage points over chain-of-thought prompting on the MODIT B2Fs and B2Fm benchmarks.
-
Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques
A survey that maps LLM applications, vulnerabilities, and defenses across eight cybersecurity domains, but with significant citation and rigor problems.
Discussion (0). Sign in to comment.