Search-Induced Issues in Web-Augmented LLM Code Generation: Detecting and Repairing Error-Inducing Pages

• URL: http://arxiv.org/abs/2603.26091v1
• Date: Fri, 27 Mar 2026 05:42:36 GMT
• Title: Search-Induced Issues in Web-Augmented LLM Code Generation: Detecting and Repairing Error-Inducing Pages
• Abstract summary: Web-augmented large language models (LLMs) offer promising capabilities for automatic code generation.<n>Live web search exposes models to unreliable or malicious content, leading to Search-Induced Issues (SII)<n>We propose Sherlock, an automated framework that enables service providers to proactively safeguard web-augmented generation systems.
• Score: 38.96179816585195
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Web-augmented large language models (LLMs) offer promising capabilities for automatic code generation. However, integrating live web search exposes models to unreliable or malicious content, leading to Search-Induced Issues (SII), a novel failure mode in which external pages mislead LLMs into producing incorrect code. This paper presents a comprehensive empirical study of the prevalence and impact of SII across three commercial search APIs and six advanced LLMs. Our analysis reveals that all evaluated web-augmented LLMs are vulnerable to SII, with root causes arising from either misaligned specifications or flawed code implementations in the searched Error-Inducing Pages (EIPs). To address this challenge, we propose Sherlock, an automated framework that enables LLM service providers to proactively safeguard web-augmented generation systems at scale. Sherlock operates as a continuous pipeline that first detects potential SII instances, then debugs them to identify the responsible EIPs and pinpoint their root causes, and finally repairs them by either annotating misaligned content or replacing erroneous code snippets with evaluated solutions from trusted sources. Experiments show that Sherlock identifies EIPs with an F1 score of up to 95% and repairs 71% to 100% of affected generations across the evaluated models, with modest computational overhead. Our findings and framework provide practical guidance for improving the reliability of web-augmented LLM-based code generation systems in real-world software engineering scenarios.

Related papers

• Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities [22.313168715963315]
  Large Language Models (LLMs) have been actively integrated into modern software systems as critical components.<n>LLMs-in-the-loop vulnerabilities, where vulnerabilities are introduced by LLMs and their dependent downstream components, such as frameworks, introduce new risks.<n>These vulnerabilities are more challenging to precisely fix, especially for those involving prompt injections where the Pass@1 rate is only 28.57%.
  arXiv  Detail & Related papers  (2026-05-27T08:11:37Z)
• LLM-GUARD: Large Language Model-Based Detection and Repair of Bugs and Security Vulnerabilities in C++ and Python [0.0]
  Large Language Models (LLMs) such as ChatGPT-4, Claude 3, and LLaMA 4 are increasingly embedded in software/application development.<n>This study presents a systematic, empirical evaluation of these three leading LLMs using a benchmark of programming errors, classic security flaws, and advanced, production-grade bugs in C++ and Python.
  arXiv  Detail & Related papers  (2025-08-22T14:30:24Z)
• Large Language Model Unlearning for Source Code [65.42425213605114]
  PROD is a novel unlearning approach that enables LLMs to forget undesired code content while preserving their code generation capabilities.<n>Our evaluation demonstrates that PROD achieves superior balance between forget quality and model utility compared to existing unlearning approaches.
  arXiv  Detail & Related papers  (2025-06-20T16:27:59Z)
• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems [50.29939179830491]
  Failure attribution in LLM multi-agent systems remains underexplored and labor-intensive.<n>We develop and evaluate three automated failure attribution methods, summarizing their corresponding pros and cons.<n>The best method achieves 53.5% accuracy in identifying failure-responsible agents but only 14.2% in pinpointing failure steps.
  arXiv  Detail & Related papers  (2025-04-30T23:09:44Z)
• Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask [30.819697001992154]
  Large Language Models are a promising tool for automated vulnerability detection.<n>Despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities?<n>This paper challenges three widely held community beliefs: that LLMs are (i) unreliable, (ii) insensitive to code patches, and (iii) performance-plateaued across model scales.
  arXiv  Detail & Related papers  (2025-04-18T05:32:47Z)
• Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
  Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.<n>Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.<n>In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
  arXiv  Detail & Related papers  (2025-02-18T03:20:50Z)
• Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
  Large language models (LLMs) generate content that can undermine trust in online discourse.<n>Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-LLM collaboration.<n>To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
  arXiv  Detail & Related papers  (2024-10-18T08:14:10Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• Detecting Phishing Sites Using ChatGPT [2.3999111269325266]
  We propose a novel system called ChatPhishDetector that utilizes Large Language Models (LLMs) to detect phishing sites.<n>Our system involves leveraging a web crawler to gather information from websites, generating prompts for LLMs based on the crawled data, and then retrieving the detection results from the responses generated by the LLMs.<n>The experimental results using GPT-4V demonstrated outstanding performance, with a precision of 98.7% and a recall of 99.6%, outperforming the detection results of other LLMs and existing systems.
  arXiv  Detail & Related papers  (2023-06-09T11:30:08Z)

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.