{"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":"/paper/bartscore-evaluating-generated-text-as-text","title":"BARTScore: Evaluating Generated Text as Text Generation","arxiv_id":"2106.11520","date":"2021-06-22","proceeding":"NeurIPS 2021 12","authors":["Weizhe Yuan","Graham Neubig","PengFei Liu"],"abstract":"A wide variety of NLP applications, such as machine translation, summarization, and dialog, involve text generation. One major challenge for these applications is how to evaluate whether such generated texts are actually fluent, accurate, or effective. In this work, we conceptualize the evaluation of generated text as a text generation problem, modeled using pre-trained sequence-to-sequence models. The general idea is that models trained to convert the generated text to/from a reference output or the source text will achieve higher scores when the generated text is better. We operationalize this idea using BART, an encoder-decoder based pre-trained model, and propose a metric BARTScore with a number of variants that can be flexibly applied in an unsupervised fashion to evaluation of text from different perspectives (e.g. informativeness, fluency, or factuality). BARTScore is conceptually simple and empirically effective. It can outperform existing top-scoring metrics in 16 of 22 test settings, covering evaluation of 16 datasets (e.g., machine translation, text summarization) and 7 different perspectives (e.g., informativeness, factuality). Code to calculate BARTScore is available at https://github.com/neulab/BARTScore, and we have released an interactive leaderboard for meta-evaluation at http://explainaboard.nlpedia.ai/leaderboard/task-meval/ on the ExplainaBoard platform, which allows us to interactively understand the strengths, weaknesses, and complementarity of each metric.","url_abs":"https://arxiv.org/abs/2106.11520v2","url_pdf":"https://arxiv.org/pdf/2106.11520v2.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":"bartscore-evaluating-generated-text-as-text","repo_url":"https://github.com/neulab/BARTScore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"bartscore-evaluating-generated-text-as-text","repo_url":"https://github.com/k-randl/self-explaining_llms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"bartscore-evaluating-generated-text-as-text","repo_url":"https://github.com/weipingfu/qgeval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"informativeness","task_name":"Informativeness"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-summarization","task_name":"Text Summarization"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.11520","atlas_url":"https://app.syntology.ai/?focus=2106.11520","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2106.11520"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.11520\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.11520"},"call":"get_concepts_for_paper(arxiv_id=\"2106.11520\")"}],"by_repo":[{"repo":"neulab/BARTScore","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2404.19563"],"harvested_for_calls":[{"arxiv_id":"2404.19563","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.19563"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.19563\")"}]},{"repo":"k-randl/self-explaining_llms","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"weipingfu/qgeval","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4bdd2cd6e5efba360ba26b113f6a9957a8e67a6290512006c0c92ed948f92f21","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}