DebugBench: Evaluating Debugging Capability of Large Language Models
read the original abstract
Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging ability are significantly limited by the risk of data leakage, the scale of the dataset, and the variety of tested bugs. To overcome these deficiencies, we introduce `DebugBench', an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python. To construct DebugBench, we collect code snippets from the LeetCode community, implant bugs into source data with GPT-4, and assure rigorous quality checks. We evaluate two commercial and four open-source models in a zero-shot scenario. We find that (1) while closed-source models exhibit inferior debugging performance compared to humans, open-source models relatively lower pass rate scores; (2) the complexity of debugging notably fluctuates depending on the bug category; (3) incorporating runtime feedback has a clear impact on debugging performance which is not always helpful. As an extension, we also compare LLM debugging and code generation, revealing a strong correlation between them for closed-source models. These findings will benefit the development of LLMs in debugging.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models
Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
-
Towards Agentic Runtime Healing
Healer uses LLMs to dynamically generate and execute runtime error-handling code, with GPT-4 recovering from 72.8% of errors across four datasets.
-
Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis
Acoda uses a genetic algorithm to optimize eight obfuscation methods that reduce LLM code analysis success rates to as low as 30% while preserving original semantics.
-
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis
ChatHLS presents a multi-agent LLM system for HLS error debugging via adaptive case expansion and QoR-aware directive optimization, reporting 32.6% better debugging than Gemini-3-pro plus speedups on kernels and accelerators.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environm...
-
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.