Logo image
Back
Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference
Conference proceeding   Open access   Peer reviewed

Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference

Yafan Huang, Sheng Di and Guanpeng Li
ICS '26: Proceedings of the 40th ACM International Conference on Supercomputing, pp.972-985
ICS '26: 2026 International Conference on Supercomputing
07/05/2026
DOI: 10.1145/3797905.3800513
Appears in  UI Libraries Support Open Access
url
https://doi.org/10.1145/3797905.3800513View
Published (Version of record) Open Access

Abstract

Large language models (LLMs) are increasingly integrated into high-performance computing (HPC) workflows, accelerating scientific discovery through diverse perspectives such as code generation and domain-specific decision-making. Yet, how soft errors propagate and affect LLM inference remains largely unexplored. To bridge this gap, we present a comprehensive study on error propagation in LLM inference, enabled by our proposed LLMFI, a configurable and deterministic fault-injection framework. Using LLMFI, we systematically inject faults across three open-weighted LLMs and thirteen representative tasks, covering reasoning, multilingual, mathematical, and coding domains. In addition, we conduct fine-grained case studies that reveal critical vulnerability patterns. Overall, our study yields 17 takeaways that advance the understanding of error propagation in LLM inference and introduces four low-overhead directions to improve reliability through software-only modification, offering practical guidance for future error detection and mitigation.
 Error Mitigation Fault Tolerance Large Language Model Inference UIOWA OA Agreement

Details

Metrics

1 Record Views
Logo image