{"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/improving-summarization-with-human-edits","title":"Improving Summarization with Human Edits","arxiv_id":"2310.05857","date":"2023-10-09","proceeding":null,"authors":["Zonghai Yao","Benjamin J Schloss","Sai P. Selvaraj"],"abstract":"Recent work has shown the promise of learning with human feedback paradigms to produce human-determined high-quality text. Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization and have obtained summary quality exceeding traditional likelihood training. In this paper, we focus on a less explored form of human feedback -- Human Edits. We propose Sequence Alignment (un)Likelihood Training (SALT), a novel technique to use both the human-edited and model-generated data together in the training loop. In addition, we demonstrate simulating Human Edits with ground truth summaries coming from existing training data -- Imitation edits, along with the model-generated summaries obtained after the training, to reduce the need for expensive human-edit data. In our experiments, we extend human feedback exploration from general domain summarization to medical domain summarization. Our results demonstrate the effectiveness of SALT in improving the summary quality with Human and Imitation Edits. Through additional experiments, we show that SALT outperforms the conventional RLHF method (designed for human preferences) -- DPO, when applied to human-edit data. We hope the evidence in our paper prompts researchers to explore, collect, and better use different human feedback approaches scalably.","url_abs":"https://arxiv.org/abs/2310.05857v3","url_pdf":"https://arxiv.org/pdf/2310.05857v3.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":"improving-summarization-with-human-edits","repo_url":"https://github.com/saiprabhakar/summarization_dpo_salt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"improving-summarization-with-human-edits","repo_url":"https://github.com/seasonyao/learnfromhumanedit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"}],"methods":[{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.05857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05857"}},"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/saiprabhakar/summarization_dpo_salt","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seasonyao/learnfromhumanedit","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":2}},"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":6,"samples":[{"code_sha256_prefix":"f120c515a0840b3c","entry":"NeedlemanWunsch","repo":"seasonyao/learnfromhumanedit","repo_kind":"official","path":"sequence_alignment/needle.py","file_url":"https://github.com/seasonyao/learnfromhumanedit/blob/HEAD/sequence_alignment/needle.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f120c515a0840b3c"}},{"code_sha256_prefix":"4b17b07f01386c76","entry":"extract_prompt","repo":"saiprabhakar/summarization_dpo_salt","repo_kind":"official","path":"trainer/trainer.py","file_url":"https://github.com/saiprabhakar/summarization_dpo_salt/blob/HEAD/trainer/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b17b07f01386c76"}},{"code_sha256_prefix":"e2c3f46dc6315f45","entry":"get_position_status","repo":"saiprabhakar/summarization_dpo_salt","repo_kind":"official","path":"sequence_alignment/needle.py","file_url":"https://github.com/saiprabhakar/summarization_dpo_salt/blob/HEAD/sequence_alignment/needle.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2c3f46dc6315f45"}},{"code_sha256_prefix":"126f423995357549","entry":"cal_SAGE","repo":"saiprabhakar/summarization_dpo_salt","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/saiprabhakar/summarization_dpo_salt/blob/HEAD/utils/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":"126f423995357549"}},{"code_sha256_prefix":"916855df75e93510","entry":"load_dataset_hg_local","repo":"saiprabhakar/summarization_dpo_salt","repo_kind":"official","path":"trainer/trainer.py","file_url":"https://github.com/saiprabhakar/summarization_dpo_salt/blob/HEAD/trainer/trainer.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":"916855df75e93510"}},{"code_sha256_prefix":"a82a905574e3548e","entry":"remove_stopword_and_punc_in_list","repo":"saiprabhakar/summarization_dpo_salt","repo_kind":"official","path":"utils/metrics.py","file_url":"https://github.com/saiprabhakar/summarization_dpo_salt/blob/HEAD/utils/metrics.py","link_basis":"harvester_set","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":"a82a905574e3548e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}