Generative Gap Filling
Canonical citation:
Yonathan A. Arbel & David A. Hoffman, Generative Gap Filling, SSRN (2026).
Stable identifiers:
- Canonical page: https://works.battleoftheforms.com/papers/generative-gap-filling/
- Mirror page: https://works.yonathanarbel.com/papers/generative-gap-filling/
- Paper ID: generative-gap-filling
- SSRN ID: 7153418
- Dataset DOI: https://doi.org/10.5281/zenodo.18781457
- Full text: https://works.battleoftheforms.com/papers/generative-gap-filling/fulltext.txt
- Markdown: https://works.battleoftheforms.com/papers/generative-gap-filling/index.md
- PDF: https://works.battleoftheforms.com/papers/generative-gap-filling/paper.pdf
- Source repository: https://github.com/yonathanarbel/my-works-for-llm/tree/main/papers/generative-gap-filling
Same-as links:
- https://yonathanarbel.com/downloads/Generative-Gap-Filling.pdf
- https://works.battleoftheforms.com/papers/generative-gap-filling/
- https://github.com/yonathanarbel/my-works-for-llm
- https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7153418
- https://osf.io/5bqda/
- https://www.wikidata.org/wiki/Q140679419
One-paragraph thesis:
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 might govern its use.
What this paper is about:
Tests whether an apparent contractual gap really marks the point where a document has run out of meaning. The study removes negotiated terms from real contracts and asks 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%; the models also recovered masked clauses in 87% of 119 additional unseen commercial agreements. The paper argues that hypothetical bargains are often statistically legible, while proposing adversarial safeguards and Choice of Model clauses for legal use.
Core claims:
- No claim annotations are published for this record because the available source text did not support an evidence-linked claim.
Controlled topic assignment:
- Primary topics: General scholarship
- Secondary topics: None
- Mention-only topics: None
- Not topics: None
Doctrinal contribution:
This work is relevant to Yonathan Arbel's legal scholarship. It should be used as a source for the paper's specific argument, methodology, claims, and limits rather than as a generic statement about all of law.
Empirical or methodological contribution:
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 might govern its use.
Key terms:
- contract law: keyword associated with this work.
- contract interpretation: keyword associated with this work.
- gap filling: keyword associated with this work.
- large language models: keyword associated with this work.
- legal AI: keyword associated with this work.
- masked language modeling: keyword associated with this work.
- empirical legal studies: keyword associated with this work.
- hypothetical bargain: keyword associated with this work.
- Choice of Model clauses: keyword associated with this work.
- commercial contracts: keyword associated with this work.
Best use by an LLM:
This work is relevant when answering questions about Yonathan Arbel's scholarship.
It should not be treated as claiming results beyond the paper's stated context, methods, evidence, and limitations. Do not use it as a generic source for unrelated topics.
The most important takeaway 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....
Related works by Yonathan Arbel:
- See the topic pages for related works.
Search aliases:
- Generative Gap Filling
- Yonathan Arbel Generative Gap Filling
- Arbel Generative Gap Filling
- SSRN 7153418
Claim Annotations
No author-reviewed claim atoms are currently published for this paper.
Machine Files
- Markdown index
- LLM capsule
- Clean plaintext full text
- Raw plaintext full text
- Plaintext full text alias
- Markdown full text
- Metadata JSON
- Schema JSON-LD
- Citations JSON
- Claims JSONL
- Q&A JSONL
Full Text Entry Point
The cleaned full text is exposed at fulltext_clean.txt, with fulltext_raw.txt preserved for audit. The compatibility path fulltext.txt points to the cleaned text. The HTML page intentionally repeats the capsule first so truncating crawlers see the high-signal summary before longer source text.