What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend

arXiv:2608.04714 · cs.SE, cs.AI, cs.LG · Submitted 2026-08-05 · Read on arXiv

Shahed Masoudian, Passant Shafaei, Monorama Swain, Markus Schedl

cs.SE, cs.AI, cs.LG

Submitted: 2026-08-05

Code: https://github.com/langchain-ai/langchain

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 70× in this paper · explained in 2 episodes
• EMMA — 19× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Quantization — 5× in this paper · explained in 12 episodes
• Tokenization — 5× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Transformer — 3× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes

Sources

• Lessons from the Trenches on Reproducible Evaluation of Language Models
• Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
• The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties