{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/jolt-joint-probabilistic-predictions-on","title":"JoLT: Joint Probabilistic Predictions on Tabular Data Using LLMs","arxiv_id":"2502.11877","date":"2025-02-17","proceeding":null,"authors":["Aliaksandra Shysheya","John Bronskill","James Requeima","Shoaib Ahmed Siddiqui","Javier Gonzalez","David Duvenaud","Richard E. Turner"],"abstract":"We introduce a simple method for probabilistic predictions on tabular data based on Large Language Models (LLMs) called JoLT (Joint LLM Process for Tabular data). JoLT uses the in-context learning capabilities of LLMs to define joint distributions over tabular data conditioned on user-specified side information about the problem, exploiting the vast repository of latent problem-relevant knowledge encoded in LLMs. JoLT defines joint distributions for multiple target variables with potentially heterogeneous data types without any data conversion, data preprocessing, special handling of missing data, or model training, making it accessible and efficient for practitioners. Our experiments show that JoLT outperforms competitive methods on low-shot single-target and multi-target tabular classification and regression tasks. Furthermore, we show that JoLT can automatically handle missing data and perform data imputation by leveraging textual side information. We argue that due to its simplicity and generality, JoLT is an effective approach for a wide variety of real prediction problems.","url_abs":"https://arxiv.org/abs/2502.11877v1","url_pdf":"https://arxiv.org/pdf/2502.11877v1.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":"jolt-joint-probabilistic-predictions-on","repo_url":"https://github.com/cambridge-mlg/jolt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"jolt-joint-probabilistic-predictions-on","repo_url":"https://github.com/requeima/llm_processes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"tabular-classification","task_name":"tabular-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.11877","atlas_url":"https://app.syntology.ai/?focus=2502.11877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11877"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cambridge-mlg/jolt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/requeima/llm_processes","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11,"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":5,"repositories":1},"listed":{"samples":11,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"dd291727dd0302a7","entry":"construct_y_str_single_categorical","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"compute_nll.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/compute_nll.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd291727dd0302a7"}},{"code_sha256_prefix":"0c5728deaf30a0b5","entry":"fix_up_old_pickle_data","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"prepare_data.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/prepare_data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c5728deaf30a0b5"}},{"code_sha256_prefix":"9365d4fa3ecbde95","entry":"hf_generate","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"hf_api.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/hf_api.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9365d4fa3ecbde95"}},{"code_sha256_prefix":"9360209261ce5655","entry":"hf_generate","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/hf_api.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/hf_api.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9360209261ce5655"}},{"code_sha256_prefix":"a72c534b1faee2fc","entry":"randomize","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/helpers.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a72c534b1faee2fc"}},{"code_sha256_prefix":"d8793531aa4c984c","entry":"repr_args","repo":"requeima/llm_processes","repo_kind":"listed","path":"experiments/classics.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/experiments/classics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8793531aa4c984c"}},{"code_sha256_prefix":"d4e32a0b5ea9d90b","entry":"rstate","repo":"requeima/llm_processes","repo_kind":"listed","path":"experiments/classics.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/experiments/classics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4e32a0b5ea9d90b"}},{"code_sha256_prefix":"25350c1df97041a7","entry":"scale_y","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/helpers.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25350c1df97041a7"}},{"code_sha256_prefix":"83f7d9232d684707","entry":"sequential_sort","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/helpers.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83f7d9232d684707"}},{"code_sha256_prefix":"48a2348a5118da9d","entry":"y_is_pure_regression","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48a2348a5118da9d"}},{"code_sha256_prefix":"e15d4cdb67eb5e56","entry":"y_is_single_categorical","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e15d4cdb67eb5e56"}},{"code_sha256_prefix":"42f13cc21dc940c7","entry":"compute_nll","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/compute_nll.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/compute_nll.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42f13cc21dc940c7"}},{"code_sha256_prefix":"863e886e0d44db0d","entry":"get_model_and_tokenizer","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"hf_api.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/hf_api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"863e886e0d44db0d"}},{"code_sha256_prefix":"6d5041d9ba211b14","entry":"get_model_and_tokenizer","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/hf_api.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/hf_api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d5041d9ba211b14"}},{"code_sha256_prefix":"17607583dc95380d","entry":"get_predicted_values_from_generated_sample","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17607583dc95380d"}},{"code_sha256_prefix":"b3833c1b2ce97a21","entry":"get_tokenizer","repo":"cambridge-mlg/jolt","repo_kind":"official","path":"hf_api.py","file_url":"https://github.com/cambridge-mlg/jolt/blob/HEAD/hf_api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3833c1b2ce97a21"}},{"code_sha256_prefix":"c544db22b8bf9aea","entry":"get_tokenizer","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/hf_api.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/hf_api.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c544db22b8bf9aea"}},{"code_sha256_prefix":"8f49db5bb884425e","entry":"prepare_data","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/prepare_data.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/prepare_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f49db5bb884425e"}},{"code_sha256_prefix":"9a0bd61896a46023","entry":"sample","repo":"requeima/llm_processes","repo_kind":"listed","path":"llm_processes/sample.py","file_url":"https://github.com/requeima/llm_processes/blob/HEAD/llm_processes/sample.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a0bd61896a46023"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}