{"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/fair-summarization-bridging-quality-and","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","arxiv_id":"2411.07521","date":"2024-11-12","proceeding":null,"authors":["Sina Bagheri Nezhad","Sayan Bandyapadhyay","Ameeta Agrawal"],"abstract":"Fairness in multi-document summarization of user-generated content remains a critical challenge in natural language processing (NLP). Existing summarization methods often fail to ensure equitable representation across different social groups, leading to biased outputs. In this paper, we introduce two novel methods for fair extractive summarization: FairExtract, a clustering-based approach, and FairGPT, which leverages GPT-3.5-turbo with fairness constraints. We evaluate these methods using Divsumm summarization dataset of White-aligned, Hispanic, and African-American dialect tweets and compare them against relevant baselines. The results obtained using a comprehensive set of summarization quality metrics such as SUPERT, BLANC, SummaQA, BARTScore, and UniEval, as well as a fairness metric F, demonstrate that FairExtract and FairGPT achieve superior fairness while maintaining competitive summarization quality. Additionally, we introduce composite metrics (e.g., SUPERT+F, BLANC+F) that integrate quality and fairness into a single evaluation framework, offering a more nuanced understanding of the trade-offs between these objectives. This work highlights the importance of fairness in summarization and sets a benchmark for future research in fairness-aware NLP models.","url_abs":"https://arxiv.org/abs/2411.07521v2","url_pdf":"https://arxiv.org/pdf/2411.07521v2.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":"fair-summarization-bridging-quality-and","repo_url":"https://github.com/PortNLP/FairEXTSummarizer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"blanc","method_name":"BLANC"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.07521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07521"}},"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":"deterministic:regex_extraction","url":"https://github.com/PortNLP/FairEXTSummarizer","reach":null}],"summary":{"ran_violates":1,"ran_fixture":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"4abfbfe28c107062","entry":"balanced","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4abfbfe28c107062"}},{"code_sha256_prefix":"4771c43876aadfaa","entry":"basic_fairlet_decomposition","repo":"PortNLP/FairEXTSummarizer","repo_kind":"official","path":"failets.py","file_url":"https://github.com/PortNLP/FairEXTSummarizer/blob/HEAD/failets.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4771c43876aadfaa"}},{"code_sha256_prefix":"21100e6d18172b50","entry":"make_fairlet","repo":"PortNLP/FairEXTSummarizer","repo_kind":"official","path":"failets.py","file_url":"https://github.com/PortNLP/FairEXTSummarizer/blob/HEAD/failets.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21100e6d18172b50"}},{"code_sha256_prefix":"445af724f7e0a399","entry":"node_fairlet_decomposition","repo":"PortNLP/FairEXTSummarizer","repo_kind":"official","path":"failets.py","file_url":"https://github.com/PortNLP/FairEXTSummarizer/blob/HEAD/failets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"445af724f7e0a399"}},{"code_sha256_prefix":"c193a8471b260af3","entry":"tree_fairlet_decomposition","repo":"PortNLP/FairEXTSummarizer","repo_kind":"official","path":"failets.py","file_url":"https://github.com/PortNLP/FairEXTSummarizer/blob/HEAD/failets.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":"c193a8471b260af3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}