mathematical-completeness-fails-to-guarantee-practical-reliability

IN derived (depth 3)

Created 2026-06-21T10:10:05+00:00 · Reviewed 2026-06-21T14:41:08+00:00

RLHF and prompting both illustrate cases where formal or mathematical specification proves insufficient for practical reliability: RLHF has a fully specified mathematical pipeline yet naive implementations fail without dozens of engineering details (motivating simpler alternatives like DPO/IPO/KTO), while prompting exhibits irreducible sensitivity and architectural injection vulnerabilities rooted in the model's inability to formally parse prompt structure. These two examples suggest that in at least some core LLM techniques, mathematical completeness or formal specification does not guarantee practical reliability.

Justifications

SL — Two independent subsystems (training-time alignment, inference-time control) exhibit the same completeness-without-reliability pattern

Antecedents (all must be IN):

  • IN rlhf-completeness-paradox-motivated-simpler-alternatives — RLHF has a fully specified mathematical pipeline (Bradley-Terry, KL penalty, PPO clipping), yet DPO, IPO, and KTO independently eliminated its separate reward model and RL loop by collapsing alignment into a single optimization step with shared β-controlled KL regularization — suggesting that the multi-component pipeline's complexity was a significant factor motivating simpler alternatives.
  • IN prompt-vulnerability-is-dual-architectural-limitation — Both prompt sensitivity (40%+ accuracy shifts from formatting) and prompt injection (inability to distinguish instructions from input) appear to be intrinsic architectural properties of instruction-following LLMs that resist improvement through scaling alone. Both phenomena may share a common factor in the model's lack of formal prompt structure parsing, though the antecedents establish each independently rather than proving a unified root cause.

Dependents

These beliefs depend on this one: