{"paper":{"title":"LLM4Log: A Systematic Review of Large Language Model-based Log Analysis","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"A review of 145 papers maps LLM use across seven log analysis tasks and distills patterns plus adoption challenges.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jinqiu Yang, Tse-Hsun Chen, Zeyang Ma","submitted_at":"2026-03-18T20:34:58Z","abstract_excerpt":"Software systems generate massive, evolving, semi-structured logs that are central to reliability engineering and AIOps, yet difficult to analyze at scale under drift and limited labels. Recent advances in pretrained Transformer models and instruction-tuned large language models (LLMs) have reshaped log analysis by enabling semantic generalization and cross-source evidence integration, but also introducing deployment risks such as context limits, latency and cost, privacy constraints, and hallucinations. This paper presents LLM4Log, a systematic review of LLM-based log analysis across the end-"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Following a structured search and manual screening protocol, we completed literature collection in November 2025 and identified 145 unique papers across seven logging tasks. We synthesize the research area through a unified, task-driven taxonomy, summarize common design patterns, and distill key lessons and open challenges for reliable real-world adoption.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The structured search protocol and manual screening captured a representative and unbiased sample of all relevant LLM-based log analysis papers published up to November 2025.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLM4Log is a systematic review of 145 papers on LLM-based log analysis that delivers a unified taxonomy, design patterns, and open challenges for reliable adoption in AIOps.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A review of 145 papers maps LLM use across seven log analysis tasks and distills patterns plus adoption challenges.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c4de1230e4eb470dd116fdd1fdcf8f434002f206f07b27911a1687123d0499d1"},"source":{"id":"2604.16359","kind":"arxiv","version":2},"verdict":{"id":"7f4f7317-0bfa-4fb8-8493-396d72290dcc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:18:09.103339Z","strongest_claim":"Following a structured search and manual screening protocol, we completed literature collection in November 2025 and identified 145 unique papers across seven logging tasks. We synthesize the research area through a unified, task-driven taxonomy, summarize common design patterns, and distill key lessons and open challenges for reliable real-world adoption.","one_line_summary":"LLM4Log is a systematic review of 145 papers on LLM-based log analysis that delivers a unified taxonomy, design patterns, and open challenges for reliable adoption in AIOps.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The structured search protocol and manual screening captured a representative and unbiased sample of all relevant LLM-based log analysis papers published up to November 2025.","pith_extraction_headline":"A review of 145 papers maps LLM use across seven log analysis tasks and distills patterns plus adoption challenges."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.16359/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}