{"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/scidqa-a-deep-reading-comprehension-dataset","title":"SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers","arxiv_id":"2411.05338","date":"2024-11-08","proceeding":null,"authors":["Shruti Singh","Nandan Sarkar","Arman Cohan"],"abstract":"Scientific literature is typically dense, requiring significant background knowledge and deep comprehension for effective engagement. We introduce SciDQA, a new dataset for reading comprehension that challenges LLMs for a deep understanding of scientific articles, consisting of 2,937 QA pairs. Unlike other scientific QA datasets, SciDQA sources questions from peer reviews by domain experts and answers by paper authors, ensuring a thorough examination of the literature. We enhance the dataset's quality through a process that carefully filters out lower quality questions, decontextualizes the content, tracks the source document across different versions, and incorporates a bibliography for multi-document question-answering. Questions in SciDQA necessitate reasoning across figures, tables, equations, appendices, and supplementary materials, and require multi-document reasoning. We evaluate several open-source and proprietary LLMs across various configurations to explore their capabilities in generating relevant and factual responses. Our comprehensive evaluation, based on metrics for surface-level similarity and LLM judgements, highlights notable performance discrepancies. SciDQA represents a rigorously curated, naturally derived scientific QA dataset, designed to facilitate research on complex scientific text understanding.","url_abs":"https://arxiv.org/abs/2411.05338v1","url_pdf":"https://arxiv.org/pdf/2411.05338v1.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":"scidqa-a-deep-reading-comprehension-dataset","repo_url":"https://github.com/yale-nlp/scidqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.05338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05338"}},"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/yale-nlp/scidqa","reach":{"status":"ok"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":10,"samples":[{"code_sha256_prefix":"73f8c0c511c1f7bc","entry":"calc_bertscore","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/evals/surface_metrics.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/evals/surface_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"73f8c0c511c1f7bc"}},{"code_sha256_prefix":"073d6a47132e69e2","entry":"calc_bleurtscore","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/evals/surface_metrics.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/evals/surface_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"073d6a47132e69e2"}},{"code_sha256_prefix":"34a4f33f933ef061","entry":"calc_rlscore","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/evals/surface_metrics.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/evals/surface_metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"34a4f33f933ef061"}},{"code_sha256_prefix":"4918a74e4c322741","entry":"full_text_cleanup","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/utils/chunking_paper_text.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/utils/chunking_paper_text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4918a74e4c322741"}},{"code_sha256_prefix":"beffd15799c043a1","entry":"get_chunks","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/llm_generation/gpt_util_file_prep.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/llm_generation/gpt_util_file_prep.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"beffd15799c043a1"}},{"code_sha256_prefix":"ccc5af8d1677878f","entry":"get_ft","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/utils/chunking_paper_text.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/utils/chunking_paper_text.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccc5af8d1677878f"}},{"code_sha256_prefix":"c678723d39c4afa0","entry":"get_rag_chunks","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/llm_generation/gpt_util_file_prep.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/llm_generation/gpt_util_file_prep.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c678723d39c4afa0"}},{"code_sha256_prefix":"1d3446d647409756","entry":"get_tabs","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/llm_generation/gpt_util_file_prep.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/llm_generation/gpt_util_file_prep.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d3446d647409756"}},{"code_sha256_prefix":"bccefed5eb5ec57f","entry":"load_metadata","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/llm_generation/gpt_ans_generation.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/llm_generation/gpt_ans_generation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bccefed5eb5ec57f"}},{"code_sha256_prefix":"2bfcd190478dd9bf","entry":"remove_illegal_characters","repo":"yale-nlp/scidqa","repo_kind":"official","path":"src/llm_generation/llm_ans_generation.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/llm_generation/llm_ans_generation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bfcd190478dd9bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}