{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/nlg-evaluation/papers/ran/1","list_of":"/task/nlg-evaluation","task":"nlg evaluation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,8],"of":8,"counts":{"archive_papers_tagged":71,"with_a_code_link":31,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":71,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/nlg-evaluation/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/long-form-information-alignment-evaluation","slug":"long-form-information-alignment-evaluation","title":"Long-Form Information Alignment Evaluation Beyond Atomic Facts","date":"2025-05-21","arxiv_id":"2505.15792","repositories_listed":0,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/long-form-information-alignment-evaluation#ran","syntology_url":"https://syntology.ai/paper/2505.15792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15792"}},"official":null}},{"url":"/paper/themis-towards-flexible-and-interpretable-nlg","slug":"themis-towards-flexible-and-interpretable-nlg","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","date":"2024-06-26","arxiv_id":"2406.18365","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/themis-towards-flexible-and-interpretable-nlg#ran","syntology_url":"https://syntology.ai/paper/2406.18365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18365"}},"official":{"repos":["PKU-ONELab/Themis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/are-llm-based-evaluators-confusing-nlg","slug":"are-llm-based-evaluators-confusing-nlg","title":"Are LLM-based Evaluators Confusing NLG Quality Criteria?","date":"2024-02-19","arxiv_id":"2402.12055","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/are-llm-based-evaluators-confusing-nlg#ran","syntology_url":"https://syntology.ai/paper/2402.12055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12055"}},"official":{"repos":["herrxy/llm-evaluator-reliability","pku-onelab/llm-evaluator-reliability"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/one-prompt-to-rule-them-all-llms-for-opinion","slug":"one-prompt-to-rule-them-all-llms-for-opinion","title":"One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation","date":"2024-02-18","arxiv_id":"2402.11683","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/one-prompt-to-rule-them-all-llms-for-opinion#ran","syntology_url":"https://syntology.ai/paper/2402.11683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11683"}},"official":{"repos":["tjsiledar/summeval-op"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-nlg-evaluation-through-pairware","slug":"zero-shot-nlg-evaluation-through-pairware","title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","date":"2023-07-15","arxiv_id":"2307.07889","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-nlg-evaluation-through-pairware#ran","syntology_url":"https://syntology.ai/paper/2307.07889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07889"}},"official":{"repos":["adianliusie/comparative-assessment"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-nlg-evaluation-metrics-a","slug":"evaluating-nlg-evaluation-metrics-a","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","date":"2023-05-24","arxiv_id":"2305.14889","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-nlg-evaluation-metrics-a#ran","syntology_url":"https://syntology.ai/paper/2305.14889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14889"}},"official":{"repos":["isle-dev/metriceval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gpteval-nlg-evaluation-using-gpt-4-with","slug":"gpteval-nlg-evaluation-using-gpt-4-with","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","date":"2023-03-29","arxiv_id":"2303.16634","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gpteval-nlg-evaluation-using-gpt-4-with#ran","syntology_url":"https://syntology.ai/paper/2303.16634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16634"}},"official":{"repos":["nlpyang/geval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/compression-transduction-and-creation-a","slug":"compression-transduction-and-creation-a","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","date":"2021-09-14","arxiv_id":"2109.06379","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compression-transduction-and-creation-a#ran","syntology_url":"https://syntology.ai/paper/2109.06379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06379"}},"official":{"repos":["tanyuqian/ctc-gen-eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"a41a9cb0300794f2912e5c19ba35ef25226079800a1d9fcce40978bbe9f5d720","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}