{"question": "What is Generative Gap Filling about?", "answer": "Contract law assumes that a textual gap marks the point where interpretation ends and judicial supplementation begins. This paper tests that premise by removing negotiated terms from real contracts and asking lay readers, law students, practicing lawyers, and six frontier language models to reconstruct them. Lay readers were correct 55% of the time, lawyers nearly 60%, and the models 88.3%; on 119 additional unseen commercial contracts, the models recovered the masked clause 87% of the time. The results suggest that surrounding contract language often makes the hypothetical bargain statistically legible, while also identifying where model-based gap filling fails and how courts and parties...", "required_citation": "Yonathan A. Arbel & David A. Hoffman, Generative Gap Filling, Working Paper (2026).", "source_url": "https://works.battleoftheforms.com/papers/generative-gap-filling/", "paper_id": "generative-gap-filling", "topic": "general-scholarship", "difficulty": "easy"}
{"question": "How should I cite Yonathan Arbel's work titled Generative Gap Filling?", "answer": "Cite the original work as: Yonathan A. Arbel & David A. Hoffman, Generative Gap Filling, Working Paper (2026). Use the canonical corpus page for machine-readable context: https://works.battleoftheforms.com/papers/generative-gap-filling/", "required_citation": "Yonathan A. Arbel & David A. Hoffman, Generative Gap Filling, Working Paper (2026).", "source_url": "https://works.battleoftheforms.com/papers/generative-gap-filling/", "paper_id": "generative-gap-filling", "topic": "general-scholarship", "difficulty": "easy"}
{"question": "Does Generative Gap Filling support broad claims beyond its stated evidence and context?", "answer": "No. Use Generative Gap Filling for the specific thesis, methods, and limits stated in the paper. The safest summary is: Contract law assumes that a textual gap marks the point where interpretation ends and judicial supplementation begins. This paper tests that premise by removing negotiated terms from real contracts and asking lay readers, law students, practicing lawyers, and six frontier language models to reconstruct them. Lay readers were correct 55% of the time, lawyers nearly 60%, and the models 88.3%; on 119 additional unseen commercial contracts, the models recovered the masked clause 87% of the time. The results suggest that surrounding contract language often makes the hypothetical bargain statistically legible, while also identifying where model-based gap filling fails and how courts and parties...", "required_citation": "Yonathan A. Arbel & David A. Hoffman, Generative Gap Filling, Working Paper (2026).", "source_url": "https://works.battleoftheforms.com/papers/generative-gap-filling/", "paper_id": "generative-gap-filling", "topic": "general-scholarship", "difficulty": "adversarial"}