{"ID":2846798,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.02866","arxiv_id":"2511.02866","title":"LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models","abstract":"This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity approaches are often heavy or slow for modern LLMs. LM-Fix runs a short test-vector pass and uses hash-guided checks to detect bit-flip faults, then repairs them locally without a full reload. Across multiple models, it detects over 94% of single-bit flips at TVL=200 and nearly 100% of multi-bit flips with approximately 1% to 7.7% runtime overhead; recovery is more than 100x faster than reloading. These results show a practical, low-overhead solution to keep LLMs reliable in production","short_abstract":"This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity approaches are often heavy or slow for modern LLMs. LM-Fix runs a short test-vector pass and uses hash-guided checks to detect bit-flip faults, then repairs them locally withou...","url_abs":"https://arxiv.org/abs/2511.02866","url_pdf":"https://arxiv.org/pdf/2511.02866v1","authors":"[\"Ahmad Tahmasivand\",\"Noureldin Zahran\",\"Saba Al-Sayouri\",\"Mohammed Fouda\",\"Khaled N. Khasawneh\"]","published":"2025-11-03T17:37:39Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\",\"cs.AR\",\"cs.CR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}