Papers for

quality assurance teams in manufacturing

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Large local language model improves sensor binding with verified plan release

Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority

Abstract: An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements unsupported by a deterministic parser are routed to a frozen local language model with four billion parameters. Plans are released only when both facts can be derived by an external gate under a sealed grammar. One canonical answer is requested from a gold-standard user when eligible. The protocol was evaluated once under a criterion fixed before benchmark construction, on 144 tasks written by isolated agent contexts without access to the gate, grammar, or experimental plan. Three contributions are established. First, candidate generation and release decisions were measured separately. Fabricated ready plans were committed on 21 of 22 routed unanswerable tasks, and all were rejected. The same 83 releases were reproduced without model calls. Second, no false release was observed among 83 releases. A one-sided 95% Clopper-Pearson upper bound of 0.0354 was obtained as a diagnostic under an independent-and-identically-distributed assumption, below the sealed 5% threshold. However, one false release was subsequently recorded among 146 releases outside the benchmark at seed 0. Third, protection against incorrect user answers was characterized. Both facts were bound from the original text on 13 of 96 answerable tasks. Incorrect answers were released in 169 of 431 pairings on the remaining tasks, including failures involving coordinate exclusion. A deployable questioning policy was not tested because eligibility was determined from the answer key. Gate sensitivity and real user behavior were not measured.

Thu 24 SeptSoftware EngineeringArtificial Intelligence
The gist
This paper looks at how to safely use a large, pre-trained local language model to help with mechatronic system setup, especially when strict rules can’t parse certain requirements. The authors created a method where the model proposes plans, but a separate checking step must verify these plans before they are accepted or released. They tested it on many tasks and found it generally did not release incorrect plans, but they did see some problems with false releases and handling wrong user answers. The study highlights how combining a big frozen model with strict controls can improve reliable decision making in complex technical setups.
Open → 2609.30219v1