mlsanityData to 7 Oct 2026

Structural Certification for Reliable Physical Design with Language Models

arXiv 2606.30107 ↗First posted 29 Jun 2026cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

An unreliable language model can be made to produce reliable physical designs if the authority to assert is moved out of the model: the model proposes, and a deterministic engine alone certifies, returning certified, impossible, or unknown. We introduce Physics-Anchored Certification (PHACT), a propose-certify loop spanning five scientific domains, and identify what makes such a certificate trustworthy. A checker that accepts a model-supplied value can be forged; deriving the certified quantity from fixed inputs instead makes forgery impossible by construction. Across eighty adversarial trials spanning two models, two decoding temperatures, and a deliberately faulted engine, this contract produced zero false certifications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 29 Jun 2026.

Builds on

15 of 22 references.

References · 15

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  9. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  10. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  11. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  12. 2022PAL: Program-aided Language Modelscited by 635
3 more
  1. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  2. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  3. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 149

Built on by

Not cited yet.