{"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","name":"nlg evaluation","slug":"nlg-evaluation","description_markdown":"Evaluate the generated text by NLG (Natural Language Generation) systems, like large language models","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":71,"papers_with_code":31,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":71,"of":71,"of_with_code":31,"tagged_in_all":71,"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":5,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"items":[{"url":"/paper/nlg-evaluation-metrics-beyond-correlation","slug":"nlg-evaluation-metrics-beyond-correlation","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","date":"2023-05-15","arxiv_id":"2305.08566","repositories_listed":7,"syntology":null},{"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/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":1,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 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":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/not-all-metrics-are-guilty-improving-nlg","slug":"not-all-metrics-are-guilty-improving-nlg","title":"Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References","date":"2023-05-24","arxiv_id":"2305.15067","repositories_listed":2,"syntology":null},{"url":"/paper/towards-a-unified-multi-dimensional-evaluator","slug":"towards-a-unified-multi-dimensional-evaluator","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","date":"2022-10-13","arxiv_id":"2210.07197","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/towards-a-unified-multi-dimensional-evaluator#ran","syntology_url":"https://syntology.ai/paper/2210.07197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07197"}},"official":{"repos":["maszhongming/unieval"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/openlgauge-an-explainable-metric-for-nlg","slug":"openlgauge-an-explainable-metric-for-nlg","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","date":"2025-03-14","arxiv_id":"2503.11858","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-evaluating-correlation-measures","slug":"analyzing-and-evaluating-correlation-measures","title":"Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation","date":"2024-10-22","arxiv_id":"2410.16834","repositories_listed":1,"syntology":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/better-than-random-reliable-nlg-human","slug":"better-than-random-reliable-nlg-human","title":"Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling","date":"2024-06-12","arxiv_id":"2406.07967","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/better-than-random-reliable-nlg-human#ran","syntology_url":"https://syntology.ai/paper/2406.07967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07967"}},"official":{"repos":["EnablerRx/CASF"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/defining-and-detecting-vulnerability-in-human","slug":"defining-and-detecting-vulnerability-in-human","title":"Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation","date":"2024-06-12","arxiv_id":"2406.07935","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-achilles-heel-of-nlg-evaluators","slug":"unveiling-the-achilles-heel-of-nlg-evaluators","title":"Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models","date":"2024-05-23","arxiv_id":"2405.14646","repositories_listed":1,"syntology":null},{"url":"/paper/debate-devil-s-advocate-based-assessment-and","slug":"debate-devil-s-advocate-based-assessment-and","title":"DEBATE: Devil's Advocate-Based Assessment and Text Evaluation","date":"2024-05-16","arxiv_id":"2405.09935","repositories_listed":1,"syntology":null},{"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":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 5 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":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-large-language-models-for-nlg","slug":"leveraging-large-language-models-for-nlg","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","date":"2024-01-13","arxiv_id":"2401.07103","repositories_listed":1,"syntology":null},{"url":"/paper/luna-a-framework-for-language-understanding","slug":"luna-a-framework-for-language-understanding","title":"LUNA: A Framework for Language Understanding and Naturalness Assessment","date":"2024-01-09","arxiv_id":"2401.04522","repositories_listed":1,"syntology":null},{"url":"/paper/towards-multiple-references-era-addressing","slug":"towards-multiple-references-era-addressing","title":"Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation","date":"2023-08-06","arxiv_id":"2308.03131","repositories_listed":1,"syntology":null},{"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/decompeval-evaluating-generated-texts-as","slug":"decompeval-evaluating-generated-texts-as","title":"DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering","date":"2023-07-13","arxiv_id":"2307.06869","repositories_listed":1,"syntology":null},{"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/describe-me-an-aucklet-generating-grounded","slug":"describe-me-an-aucklet-generating-grounded","title":"Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions","date":"2023-03-07","arxiv_id":"2303.04053","repositories_listed":1,"syntology":null},{"url":"/paper/is-chatgpt-a-good-nlg-evaluator-a-preliminary","slug":"is-chatgpt-a-good-nlg-evaluator-a-preliminary","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","date":"2023-03-07","arxiv_id":"2303.04048","repositories_listed":1,"syntology":null},{"url":"/paper/clse-corpus-of-linguistically-significant","slug":"clse-corpus-of-linguistically-significant","title":"CLSE: Corpus of Linguistically Significant Entities","date":"2022-11-04","arxiv_id":"2211.02423","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-errors-are-equal-learning-text","slug":"not-all-errors-are-equal-learning-text","title":"Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis","date":"2022-10-10","arxiv_id":"2210.05035","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-do-that-simpler-simple-efficient-high","slug":"can-we-do-that-simpler-simple-efficient-high","title":"EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics","date":"2022-09-20","arxiv_id":"2209.09593","repositories_listed":1,"syntology":null},{"url":"/paper/near-negative-distinction-giving-a-second","slug":"near-negative-distinction-giving-a-second","title":"Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets","date":"2022-05-13","arxiv_id":"2205.06871","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-cross-lingual-gaps-during-leveraging","slug":"bridging-cross-lingual-gaps-during-leveraging","title":"Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding","date":"2022-04-16","arxiv_id":"2204.07834","repositories_listed":1,"syntology":null},{"url":"/paper/active-evaluation-efficient-nlg-evaluation-1","slug":"active-evaluation-efficient-nlg-evaluation-1","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","date":"2022-03-11","arxiv_id":"2203.06063","repositories_listed":1,"syntology":null},{"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"]}}},{"url":"/paper/perturbation-checklists-for-evaluating-nlg","slug":"perturbation-checklists-for-evaluating-nlg","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","date":"2021-09-13","arxiv_id":"2109.05771","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-automatic-metrics-for-the","slug":"a-study-of-automatic-metrics-for-the","title":"A Study of Automatic Metrics for the Evaluation of Natural Language Explanations","date":"2021-03-15","arxiv_id":"2103.08545","repositories_listed":1,"syntology":null},{"url":"/paper/why-we-need-new-evaluation-metrics-for-nlg","slug":"why-we-need-new-evaluation-metrics-for-nlg","title":"Why We Need New Evaluation Metrics for NLG","date":"2017-07-21","arxiv_id":"1707.06875","repositories_listed":1,"syntology":null},{"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":null,"slug":"beyond-one-size-fits-all-inversion-learning","title":"Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts","date":"2025-04-29","arxiv_id":"2504.21117","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepseek-vs-o3-mini-how-well-can-reasoning","title":"DeepSeek vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?","date":"2025-04-10","arxiv_id":"2504.08120","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-multilingual-nlg-evaluation","title":"Exploring the Multilingual NLG Evaluation Abilities of LLM-Based Evaluators","date":"2025-03-06","arxiv_id":"2503.04360","repositories_listed":0,"syntology":null},{"url":null,"slug":"sageval-the-frontiers-of-satisfactory-agent","title":"SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended text","date":"2024-11-25","arxiv_id":"2411.16077","repositories_listed":0,"syntology":null},{"url":null,"slug":"ev2r-evaluating-evidence-retrieval-in","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","date":"2024-11-08","arxiv_id":"2411.05375","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-are-active-critics-in","title":"Large Language Models Are Active Critics in NLG Evaluation","date":"2024-10-14","arxiv_id":"2410.10724","repositories_listed":0,"syntology":null},{"url":null,"slug":"dhp-benchmark-are-llms-good-nlg-evaluators","title":"DHP Benchmark: Are LLMs Good NLG Evaluators?","date":"2024-08-25","arxiv_id":"2408.13704","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-feedback-reason-refer-a-novel","title":"ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models","date":"2024-07-16","arxiv_id":"2407.12877","repositories_listed":0,"syntology":null},{"url":null,"slug":"waterjudge-quality-detection-trade-off-when","title":"WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models","date":"2024-03-28","arxiv_id":"2403.19548","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-nlg-evaluation-current-status-and","title":"LLM-based NLG Evaluation: Current Status and Challenges","date":"2024-02-02","arxiv_id":"2402.01383","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-pitfalls-of-defining-hallucination","title":"The Pitfalls of Defining Hallucination","date":"2024-01-15","arxiv_id":"2401.07897","repositories_listed":0,"syntology":null},{"url":null,"slug":"coascore-chain-of-aspects-prompting-for-nlg","title":"CoAScore: Chain-of-Aspects Prompting for NLG Evaluation","date":"2023-12-16","arxiv_id":"2312.10355","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-eval-generalizable-multi-aspect-text","title":"X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects","date":"2023-11-15","arxiv_id":"2311.08788","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-model-evaluation-as-narrowing-the","title":"Rethinking Model Evaluation as Narrowing the Socio-Technical Gap","date":"2023-06-01","arxiv_id":"2306.03100","repositories_listed":0,"syntology":null},{"url":null,"slug":"dolphin-a-challenging-and-diverse-benchmark","title":"Dolphin: A Challenging and Diverse Benchmark for Arabic NLG","date":"2023-05-24","arxiv_id":"2305.14989","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-robust-evaluation-of-generated-text","title":"Dialect-robust Evaluation of Generated Text","date":"2022-11-02","arxiv_id":"2211.00922","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlg-metricverse-an-end-to-end-library-for","title":"NLG-Metricverse: An End-to-End Library for Evaluating Natural Language Generation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-interpreted-checklist-for-meaning-1","title":"A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation – through the Lens of Semantic Similarity Rating","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-interpreted-checklist-for-meaning","title":"A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation -- through the Lens of Semantic Similarity Rating","date":"2022-05-24","arxiv_id":"2205.12176","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-human-is-human-evaluation-improving-the","title":"The Authenticity Gap in Human Evaluation","date":"2022-05-24","arxiv_id":"2205.11930","repositories_listed":0,"syntology":null},{"url":null,"slug":"deconstructing-nlg-evaluation-evaluation","title":"Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications","date":"2022-05-13","arxiv_id":"2205.06828","repositories_listed":0,"syntology":null},{"url":null,"slug":"repairing-the-cracked-foundation-a-survey-of","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","date":"2022-02-14","arxiv_id":"2202.06935","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-natural-language-generation","title":"A Survey of Natural Language Generation","date":"2021-12-22","arxiv_id":"2112.11739","repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-an-imagination-based-automatic-1","title":"ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-augmented-relevance-score","title":"Language Model Augmented Relevance Score","date":"2021-08-19","arxiv_id":"2108.08485","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-that-s-human-is-not-gold-evaluating-human-1","title":"All That's `Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mipe-a-metric-independent-pipeline-for","title":"MIPE: A Metric Independent Pipeline for Effective Code-Mixed NLG Evaluation","date":"2021-07-24","arxiv_id":"2107.11534","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-that-s-human-is-not-gold-evaluating-human","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","date":"2021-06-30","arxiv_id":"2107.00061","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-evaluation-efficient-nlg-evaluation","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","date":"2021-06-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-an-imagination-based-automatic","title":"ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation","date":"2021-06-10","arxiv_id":"2106.05970","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tutorial-on-evaluation-metrics-used-in","title":"A Tutorial on Evaluation Metrics used in Natural Language Generation","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-rules-on-the-use-of-grammars-and","title":"Evaluation rules! On the use of grammars and rule-based systems for NLG evaluation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-evaluation-metrics-used-for-nlg","title":"A Survey of Evaluation Metrics Used for NLG Systems","date":"2020-08-27","arxiv_id":"2008.12009","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-text-generation-a-survey","title":"Evaluation of Text Generation: A Survey","date":"2020-06-26","arxiv_id":"2006.14799","repositories_listed":0,"syntology":null},{"url":null,"slug":"agreement-is-overrated-a-plea-for-correlation","title":"Agreement is overrated: A plea for correlation to assess human evaluation reliability","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-use-of-rating-and-likert-scales-in","title":"The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"treat-the-system-like-a-human-student","title":"Treat the system like a human student: Automatic naturalness evaluation of generated text without reference texts","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-the-state-of-the-art-in-natural","title":"Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation","date":"2017-03-29","arxiv_id":"1703.09902","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-snapshot-of-nlg-evaluation-practices-2005","title":"A Snapshot of NLG Evaluation Practices 2005 - 2014","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/nlg-evaluation/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/nlg-evaluation/papers/ran/1","json":"/task/nlg-evaluation/papers/ran/1.json","rows":8}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"b339ee51749f79f142ea17525787568be03d3b0e76a566ee418fb48e14d1bff7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}