Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads
The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped. Existing bug localization techniques are either prohibitively expensive, requiring minutes of agentic reasoning and thousands of generated tokens per file, and/or operate at coarse function-level granularity unsuitable for precise debugging. While works that focus on line-level granularity and are more light-weight are often limited in their performance or context size. We introduce a novel line-level bug localization approach that addresses these limitations through three key contributions: (1) a token alignment algorithm that overcomes fundamental tokenization challenges in previous work, (2) a lightweight multi-task LLM for bug localization (MLC) enabling efficient line-level bug classification, and (3) an optimized training recipe for multi-line prediction. Our method achieves state-of-the-art performance among similar setups on line-level bug localization with full-file context. At the same time we reach comparable performance to agentic approaches on Defects4J and PypiBugs benchmarks while reducing inference latency by orders of magnitudes, requiring only a single generated token per file. We further demonstrate strong generalization by introducing and evaluating on a small out-of-domain evaluation datasets in Python. We will open source our code, models, and datasets upon acceptance.
Code (0)
등록된 구현이 없습니다.
Tasks
Code GenerationSimilar Papers 제목 키워드 기반
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
Extracting sentence embeddings from large language models (LLMs) is a practical direction, as it requires neither additional data nor fine-tuning. Previous studies usually focus on prompt engineering to guide LLMs to enc…
Prompt EngineeringSemantic Textual SimilaritySentenceSentence Embedding+3Auxiliary Metrics Help Decoding Skill Neurons in the Wild
Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable me…
Natural Language InferenceArithmetic ReasoningText GenerationAnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models
Accurately explaining hidden patterns in multi-aspect data has typically been done by leveraging labels and/or accompanying auxiliary metadata. However, labels and auxiliary data may be inaccurate (e.g. nonstandard, inco…
Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation
Training or finetuning large-scale language models (LLMs) such as GPT-3 requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One practical a…
Data AugmentationFew-Shot Text ClassificationLanguage ModelingLanguage Modelling+2GIRNet: Interleaved Multi-Task Recurrent State Sequence Models
In several natural language tasks, labeled sequences are available in separate domains (say, languages), but the goal is to label sequences with mixed domain (such as code-switched text). Or, we may have available models…
Part-Of-Speech TaggingPositionSentiment AnalysisSentiment Classification