FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation
Existing approaches rely on static supervised data, which quickly saturates on limited annotations. In this paper, we introduce FORMULASPIN, a self-play framework that breaks the ceiling of supervised fine-tuning by enabling iterative self-improvement without any additional data. Vanilla SPIN fails on this task: it uniformly penalizes every non-matching output, so execution-equivalent alternatives are punished as negatives in one example while serving as ground truth in another, producing contradictory gradients.
- ▪Existing approaches rely on static supervised data, which quickly saturates on limited annotations.
- ▪In this paper, we introduce FORMULASPIN, a self-play framework that breaks the ceiling of supervised fine-tuning by enabling iterative self-improvement without any additional data.
- ▪Vanilla SPIN fails on this task: it uniformly penalizes every non-matching output, so execution-equivalent alternatives are punished as negatives in one example while serving as ground truth in another, producing contradictory gradients.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2607.19354 |
| Publication time | Thu, 23 Jul 2026 00:00:00 -0400 |
| Retrieval time | 2026-07-23T04:57:25.938Z |
| Last seen | 2026-07-23T08:18:15.991Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | QpM2lczuhNVI |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2607.19354 (cs) [Submitted on 21 May 2026] Title:FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation Authors:Cy Xie View a PDF of the paper titled FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation, by Cy Xie View PDF HTML (experimental) Abstract:Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier. Existing approaches rely on static supervised data, which quickly saturates on limited annotations. In this paper, we introduce FORMULASPIN, a self-play framework that breaks the ceiling of supervised fine-tuning by enabling iterative self-improvement without any additional data.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
