{"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/citebench-a-benchmark-for-scientific-citation","title":"CiteBench: A benchmark for Scientific Citation Text Generation","arxiv_id":"2212.09577","date":"2022-12-19","proceeding":null,"authors":["Martin Funkquist","Ilia Kuznetsov","Yufang Hou","Iryna Gurevych"],"abstract":"Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of prior work. To address this, the task of citation text generation aims to produce accurate textual summaries given a set of papers-to-cite and the citing paper context. Due to otherwise rare explicit anchoring of cited documents in the citing paper, citation text generation provides an excellent opportunity to study how humans aggregate and synthesize textual knowledge from sources. Yet, existing studies are based upon widely diverging task definitions, which makes it hard to study this task systematically. To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into the task definition and evaluation to guide future research in citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.","url_abs":"https://arxiv.org/abs/2212.09577v3","url_pdf":"https://arxiv.org/pdf/2212.09577v3.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":"citebench-a-benchmark-for-scientific-citation","repo_url":"https://github.com/ukplab/citebench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.09577","atlas_url":"https://app.syntology.ai/?focus=2212.09577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09577"}},"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/ukplab/citebench","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"a5e54b7f79d77838","entry":"concat_batch_input","repo":"ukplab/citebench","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5e54b7f79d77838"}},{"code_sha256_prefix":"3e9015b29595f34a","entry":"concat_single_input","repo":"ukplab/citebench","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e9015b29595f34a"}},{"code_sha256_prefix":"1926116713ace14c","entry":"contains_ref_to_target_paper","repo":"ukplab/citebench","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1926116713ace14c"}},{"code_sha256_prefix":"9f85781e21e7f9c2","entry":"convert_input_docs_to_unified_format","repo":"ukplab/citebench","repo_kind":"official","path":"src/data_processing/related_work_benchmark_construction.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/data_processing/related_work_benchmark_construction.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f85781e21e7f9c2"}},{"code_sha256_prefix":"72d6e76affca1501","entry":"convert_to_float","repo":"ukplab/citebench","repo_kind":"official","path":"src/data_processing/aggregate_rouge2_scores.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/data_processing/aggregate_rouge2_scores.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72d6e76affca1501"}},{"code_sha256_prefix":"1029e3cc80585167","entry":"process_files","repo":"ukplab/citebench","repo_kind":"official","path":"src/data_processing/convert_multix_outputs.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/data_processing/convert_multix_outputs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1029e3cc80585167"}},{"code_sha256_prefix":"407656acf8143d79","entry":"remove_leading_brackets","repo":"ukplab/citebench","repo_kind":"official","path":"src/data_processing/related_work_benchmark_construction.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/data_processing/related_work_benchmark_construction.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"407656acf8143d79"}},{"code_sha256_prefix":"03f7584e429a9706","entry":"sent_contains_cite","repo":"ukplab/citebench","repo_kind":"official","path":"src/data_processing/convert_to_scicite.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/data_processing/convert_to_scicite.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03f7584e429a9706"}},{"code_sha256_prefix":"9ea5d3d43f24f0c3","entry":"get_data_aburaed_et_al","repo":"ukplab/citebench","repo_kind":"official","path":"src/data_processing/related_work_benchmark_construction.py","file_url":"https://github.com/ukplab/citebench/blob/HEAD/src/data_processing/related_work_benchmark_construction.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ea5d3d43f24f0c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}