Detecção de Conflitos Semânticos com Testes Gerados por LLM

• URL: http://arxiv.org/abs/2507.06762v2
• Date: Wed, 13 Aug 2025 18:37:04 GMT
• Title: Detecção de Conflitos Semânticos com Testes Gerados por LLM
• Authors: Nathalia Barbosa, Paulo Borba, Léuson Da Silva,
• Abstract summary: We propose and integrate a new test generation tool based on Code Llama 70B into SMAT.<n>SMAT relies on generating and executing unit tests: if a test fails on the base version, passes on a developer's modified version, but fails again after merging with another developer's changes, a semantic conflict is indicated.<n>Results indicate that, although LLM-based test generation remains challenging and computationally expensive in complex scenarios, there is promising potential for improving semantic conflict detection.
• Score: 1.201626478128059
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic conflicts arise when a developer introduces changes to a codebase that unintentionally affect the behavior of changes integrated in parallel by other developers. Traditional merge tools are unable to detect such conflicts, so complementary tools like SMAT have been proposed. SMAT relies on generating and executing unit tests: if a test fails on the base version, passes on a developer's modified version, but fails again after merging with another developer's changes, a semantic conflict is indicated. While SMAT is effective at detecting conflicts, it suffers from a high rate of false negatives, partly due to the limitations of unit test generation tools such as Randoop and Evosuite. To investigate whether large language models (LLMs) can overcome these limitations, we propose and integrate a new test generation tool based on Code Llama 70B into SMAT. We explore the model's ability to generate tests using different interaction strategies, prompt contents, and parameter configurations. Our evaluation uses two samples: a benchmark with simpler systems from related work, and a more significant sample based on complex, real-world systems. We assess the effectiveness of the new SMAT extension in detecting conflicts. Results indicate that, although LLM-based test generation remains challenging and computationally expensive in complex scenarios, there is promising potential for improving semantic conflict detection.

Related papers

• ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases [58.411135609139855]
  "Shortcuts" to complete tasks pose significant risks for reliable assessment and deployment of large language models.<n>We introduce ImpossibleBench, a benchmark framework that measures LLM agents' propensity to exploit test cases.<n>As a practical framework, ImpossibleBench is not just an evaluation but a versatile tool.
  arXiv  Detail & Related papers  (2025-10-23T06:58:32Z)
• That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation [55.78914774437411]
  Large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt.<n>We propose a domain-agnostic framework for constructing and interpreting such conflicts.<n>We show that activation-level steering can achieve up to a textbf12.6% improvement in steering success over a random baseline.
  arXiv  Detail & Related papers  (2025-10-21T22:27:56Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models [60.713908578319256]
  We propose Direct Discrepancy Learning (DDL) to optimize the detector with task-oriented knowledge.<n>Built upon this, we introduce DetectAnyLLM, a unified detection framework that achieves state-of-the-art MGTD performance.<n>MIRAGE samples human-written texts from 10 corpora across 5 text-domains, which are then re-generated or revised using 17 cutting-edge LLMs.
  arXiv  Detail & Related papers  (2025-09-15T10:59:57Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• Impact of Code Context and Prompting Strategies on Automated Unit Test Generation with Modern General-Purpose Large Language Models [0.0]
  Generative AI is gaining increasing attention in software engineering.<n>Unit tests constitute the majority of test cases and are often schematic.<n>This paper investigates the impact of code context and prompting strategies on the quality and adequacy of unit tests.
  arXiv  Detail & Related papers  (2025-07-18T11:23:17Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search [51.91311158085973]
  multimodal misinformation often arises from mixed forgery sources, requiring dynamic reasoning and adaptive verification.<n>We propose T2Agent, a novel misinformation detection agent that incorporates a toolkit with Monte Carlo Tree Search.<n>Extensive experiments show that T2Agent consistently outperforms existing baselines on challenging mixed-source multimodal misinformation benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T09:50:55Z)
• Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs [60.881609323604685]
  Large Language Models (LLMs) accessed via black-box APIs introduce a trust challenge.<n>Users pay for services based on advertised model capabilities.<n> providers may covertly substitute the specified model with a cheaper, lower-quality alternative to reduce operational costs.<n>This lack of transparency undermines fairness, erodes trust, and complicates reliable benchmarking.
  arXiv  Detail & Related papers  (2025-04-07T03:57:41Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• Test smells in LLM-Generated Unit Tests [16.061139428298986]
  This paper presents the first multi-benchmark, large-scale analysis of test smell diffusion in LLM-generated unit tests.<n>Our study draws on 20,505 class-level suites from four LLMs (GPT-3.5, GPT-4, Mistral 7B, Mixtral 8x7B), 972 method-level cases from TestBench, 14,469 EvoSuite tests, and 779,585 human-written tests from 34,635 open-source Java projects.
  arXiv  Detail & Related papers  (2024-10-14T15:35:44Z)
• CONGRA: Benchmarking Automatic Conflict Resolution [3.9910625211670485]
  ConGra is a benchmarking scheme designed to evaluate the performance of software merging tools. We build a large-scale evaluation dataset based on 44,948 conflicts from 34 real-world projects.
  arXiv  Detail & Related papers  (2024-09-21T12:21:41Z)
• AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge [57.66282463340297]
  Knowledge conflict arises from discrepancies between information in the context of a large language model and the knowledge stored in its parameters.<n>We propose a fine-grained, instance-level approach called AdaCAD, which dynamically infers the weight of adjustment based on the degree of conflict.<n>We show that ADACAD consistently outperforms other decoding baselines with average QA accuracy gains of 14.21% (absolute) over a static contrastive baseline, and improves the factuality of summaries by 6.19 (AlignScore)
  arXiv  Detail & Related papers  (2024-09-11T16:35:18Z)
• Fix the Tests: Augmenting LLMs to Repair Test Cases with Static Collector and Neural Reranker [9.428021853841296]
  We propose SYNTER, a novel approach to automatically repair obsolete test cases via precise and concise TROCtxs construction. With the augmentation of constructed TROCtxs, hallucinations are reduced by 57.1%.
  arXiv  Detail & Related papers  (2024-07-04T04:24:43Z)
• SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents [10.730852617039451]
  We investigate the capability of LLM-based Code Agents to formalize user issues into test cases.<n>We propose a novel benchmark based on popular GitHub repositories, containing real-world issues, ground-truth bug-fixes, and golden tests.<n>We find that LLMs generally perform surprisingly well at generating relevant test cases, with Code Agents designed for code repair exceeding the performance of systems designed for test generation.
  arXiv  Detail & Related papers  (2024-06-18T14:54:37Z)
• Learning to Use Tools via Cooperative and Interactive Agents [58.77710337157665]
  Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. We propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. Our experiments on three datasets show that the LLMs, when equipped with ConAgents, outperform baselines with substantial improvement.
  arXiv  Detail & Related papers  (2024-03-05T15:08:16Z)
• Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM [32.44432906540792]
  We present SymPrompt, a code-aware prompting strategy for large language models in test generation. SymPrompt enhances correct test generations by a factor of 5 and bolsters relative coverage by 26% for CodeGen2. Notably, when applied to GPT-4, SymPrompt improves coverage by over 2x compared to baseline prompting strategies.
  arXiv  Detail & Related papers  (2024-01-31T18:21:49Z)
• Detecting Semantic Conflicts with Unit Tests [5.273883263686449]
  Branching and merging are common practices in software development, increasing developer's productivity. Modern merge techniques can resolve textual conflicts automatically, but they fail when the conflict arises at the semantic level. We proposeSemAntic Merge, a semantic merge tool based on the automated generation of unit tests.
  arXiv  Detail & Related papers  (2023-10-03T19:36:28Z)
• Fault-Aware Neural Code Rankers [64.41888054066861]
  We propose fault-aware neural code rankers that can predict the correctness of a sampled program without executing it. Our fault-aware rankers can significantly increase the pass@1 accuracy of various code generation models.
  arXiv  Detail & Related papers  (2022-06-04T22:01:05Z)
• D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis [55.15995704119158]
  We propose D2A, a differential analysis based approach to label issues reported by static analysis tools. We use D2A to generate a large labeled dataset to train models for vulnerability identification.
  arXiv  Detail & Related papers  (2021-02-16T07:46:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.