{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/spreadsheetllm-encoding-spreadsheets-for","title":"SpreadsheetLLM: Encoding Spreadsheets for Large Language Models","arxiv_id":"2407.09025","date":"2024-07-12","proceeding":null,"authors":["Yuzhang Tian","Jianbo Zhao","Haoyu Dong","Junyu Xiong","Shiyu Xia","Mengyu Zhou","Yun Lin","José Cambronero","Yeye He","Shi Han","Dongmei Zhang"],"abstract":"Spreadsheets, with their extensive two-dimensional grids, various layouts, and diverse formatting options, present notable challenges for large language models (LLMs). In response, we introduce SpreadsheetLLM, pioneering an efficient encoding method designed to unleash and optimize LLMs' powerful understanding and reasoning capability on spreadsheets. Initially, we propose a vanilla serialization approach that incorporates cell addresses, values, and formats. However, this approach was limited by LLMs' token constraints, making it impractical for most applications. To tackle this challenge, we develop SheetCompressor, an innovative encoding framework that compresses spreadsheets effectively for LLMs. It comprises three modules: structural-anchor-based compression, inverse index translation, and data-format-aware aggregation. It significantly improves performance in spreadsheet table detection task, outperforming the vanilla approach by 25.6% in GPT4's in-context learning setting. Moreover, fine-tuned LLM with SheetCompressor has an average compression ratio of 25 times, but achieves a state-of-the-art 78.9% F1 score, surpassing the best existing models by 12.3%. Finally, we propose Chain of Spreadsheet for downstream tasks of spreadsheet understanding and validate in a new and demanding spreadsheet QA task. We methodically leverage the inherent layout and structure of spreadsheets, demonstrating that SpreadsheetLLM is highly effective across a variety of spreadsheet tasks.","url_abs":"https://arxiv.org/abs/2407.09025v1","url_pdf":"https://arxiv.org/pdf/2407.09025v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"spreadsheetllm-encoding-spreadsheets-for","repo_url":"https://github.com/microsoft/TUTA_table_understanding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"spreadsheetllm-encoding-spreadsheets-for","repo_url":"https://github.com/microsoft/hitab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"table-detection","task_name":"Table Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.09025","atlas_url":"https://app.syntology.ai/?focus=2407.09025","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2407.09025"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.09025\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.09025"},"call":"get_concepts_for_paper(arxiv_id=\"2407.09025\")"}],"by_repo":[{"repo":"microsoft/TUTA_table_understanding","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.12537"],"harvested_for_calls":[{"arxiv_id":"2010.12537","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.12537"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.12537\")"}]},{"repo":"microsoft/hitab","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2108.06712"],"harvested_for_calls":[{"arxiv_id":"2108.06712","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2108.06712"},"call":"get_harvested_code_for_paper(arxiv_id=\"2108.06712\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6a154e9e164321f996639047b95a1c566e66bd7d855150186df4090f44c5a9b3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}