mlsanityData to 7 Oct 2026

LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models

arXiv 2511.02866 ↗First posted 3 Nov 2025cs.SE cs.AI cs.ARcited by 3

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

18 of 42 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2016Pointer Sentinel Mixture Modelscited by 2,992
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  7. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  8. 2024Phi-4 Technical Reportcited by 675
  9. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  10. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 106
  11. 2024EasyJailbreak: A Unified Framework for Jailbreaking Large Language Modelscited by 57
  12. 2019FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activationcited by 31
6 more
  1. 2025GPUHammer: Rowhammer Attacks on GPU Memories are Practicalcited by 11
  2. 2025On Jailbreaking Quantized Language Models Through Fault Injection Attackscited by 8
  3. 2024BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attackscited by 7
  4. 2020Revisiting RowHammer: An Experimental Analysis of Modern DRAM Devices and Mitigation Techniquescited by 5
  5. 2023Retrospective: Flipping Bits in Memory Without Accessing Them: An Experimental Study of DRAM Disturbance Errorscited by 5
  6. 2025Bit-Flip Fault Attack: Crushing Graph Neural Networks via Gradual Bit Searchcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Same Game, Different Story: A Minimal Conservative Strategic Robustness Benchmark for Large Language Model Agentscited by 1
  2. 2025BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMscited by 0
  3. 2026Faults That Fortify: CNN Adversarial Robustness via GPU Undervoltingcited by 0