{"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/freb-tqa-a-fine-grained-robustness-evaluation","title":"FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering","arxiv_id":"2404.18585","date":"2024-04-29","proceeding":null,"authors":["Wei Zhou","Mohsen Mesgar","Heike Adel","Annemarie Friedrich"],"abstract":"Table Question Answering (TQA) aims at composing an answer to a question based on tabular data. While prior research has shown that TQA models lack robustness, understanding the underlying cause and nature of this issue remains predominantly unclear, posing a significant obstacle to the development of robust TQA systems. In this paper, we formalize three major desiderata for a fine-grained evaluation of robustness of TQA systems. They should (i) answer questions regardless of alterations in table structure, (ii) base their responses on the content of relevant cells rather than on biases, and (iii) demonstrate robust numerical reasoning capabilities. To investigate these aspects, we create and publish a novel TQA evaluation benchmark in English. Our extensive experimental analysis reveals that none of the examined state-of-the-art TQA systems consistently excels in these three aspects. Our benchmark is a crucial instrument for monitoring the behavior of TQA systems and paves the way for the development of robust TQA systems. We release our benchmark publicly.","url_abs":"https://arxiv.org/abs/2404.18585v1","url_pdf":"https://arxiv.org/pdf/2404.18585v1.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":"freb-tqa-a-fine-grained-robustness-evaluation","repo_url":"https://github.com/hiyouga/llama-factory","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"freb-tqa-a-fine-grained-robustness-evaluation","repo_url":"https://github.com/boschresearch/freb-tqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.18585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18585"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/boschresearch/freb-tqa","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hiyouga/llama-factory","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"5bb9e3917fa7d163","entry":"col_shuffling","repo":"boschresearch/freb-tqa","repo_kind":"official","path":"code/perturbation.py","file_url":"https://github.com/boschresearch/freb-tqa/blob/HEAD/code/perturbation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5bb9e3917fa7d163"}},{"code_sha256_prefix":"4cea8dfbeeb6c20e","entry":"find_answer_float","repo":"boschresearch/freb-tqa","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/boschresearch/freb-tqa/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4cea8dfbeeb6c20e"}},{"code_sha256_prefix":"3f7ad06ea06a753f","entry":"generate_demostration","repo":"boschresearch/freb-tqa","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/boschresearch/freb-tqa/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3f7ad06ea06a753f"}},{"code_sha256_prefix":"2b34edb53576e017","entry":"reformat_table","repo":"boschresearch/freb-tqa","repo_kind":"official","path":"code/utils.py","file_url":"https://github.com/boschresearch/freb-tqa/blob/HEAD/code/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2b34edb53576e017"}},{"code_sha256_prefix":"d297675b7c31cdf8","entry":"row_shuffling","repo":"boschresearch/freb-tqa","repo_kind":"official","path":"code/perturbation.py","file_url":"https://github.com/boschresearch/freb-tqa/blob/HEAD/code/perturbation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d297675b7c31cdf8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}