LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering

arXiv:2608.31102 · cs.SE, cs.AI, cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.SE, cs.AI, cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Benchmark — 37× in this paper · explained in 2 episodes
• Distillation — 26× in this paper · explained in 2 episodes
• Core — 6× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Failure Modes — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Failure-Driven Synthesis — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Large Language Models Trained on Code
• The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models
• Quantifying Variance in Evaluation Benchmarks
• Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
• Dynamic Stability of LLM-Generated Code
• Effectively Controlling Reasoning Models through Thinking Intervention
• Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement
• PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
• When Elo Lies: Hidden Biases in Codeforces-Based Evaluation of Large Language Models

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