Papers › TextBox 2.0: A Text Generation Library with Pre-trained Language Models

TextBox 2.0: A Text Generation Library with Pre-trained Language Models

26 Dec 2022arXiv:2212.13005archive 2025-07-28

Tianyi Tang, Junyi Li, Zhipeng Chen, Yiwen Hu, Zhuohao Yu, Wenxun Dai, Zican Dong, Xiaoxue Cheng, Yuhao Wang, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen

To facilitate research on text generation, this paper presents a comprehensive and unified library, TextBox 2.0, focusing on the use of pre-trained language models (PLMs). To be comprehensive, our library covers $13$ common text generation tasks and their corresponding $83$ datasets and further incorporates $45$ PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLMs. We also implement $4$ efficient training strategies and provide $4$ generation objectives for pre-training new PLMs from scratch. To be unified, we design the interfaces to support the entire research pipeline (from data loading to training and evaluation), ensuring that each step can be fulfilled in a unified way. Despite the rich functionality, it is easy to use our library, either through the friendly Python API or command line. To validate the effectiveness of our library, we conduct extensive experiments and exemplify four types of research scenarios. The project is released at the link: https://github.com/RUCAIBox/TextBox.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2212.13005")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

RUCAIBox/TextBox officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran

Licence: 0 of the 1 sample are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from RUCAIBox/TextBox. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

AbstractModel RUCAIBox/TextBox/textbox/model/abstract_model.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 36d020284e254099 · report

Tasks

Abstractive Text SummarizationData-to-Text GenerationDialogueMachine TranslationQuestion AnsweringQuestion GenerationStory GenerationStyle TransferTask-Oriented Dialogue SystemsText GenerationText Simplification

Datasets

Introduced by this paper, per the archive.

TextBox 2.0

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN/Daily Mail BART (TextBox 2.0) ROUGE-1 44.47 #1 of 4 Archive leaderboard report
Abstractive Text Summarization CNN/Daily Mail BART (TextBox 2.0) ROUGE-2 21.5 #1 of 4 Archive leaderboard report
Abstractive Text Summarization CNN/Daily Mail BART (TextBox 2.0) ROUGE-L 41.35 #1 of 4 Archive leaderboard report
Data-to-Text Generation WebNLG BART (TextBox 2.0) BLEU-4 67.33 #20 of 20 Archive leaderboard report
Data-to-Text Generation WebNLG BART (TextBox 2.0) METEOR 47.78 #20 of 20 Archive leaderboard report
Data-to-Text Generation WebNLG BART (TextBox 2.0) ROUGE-L 76.83 #20 of 20 Archive leaderboard report
Dialogue Persona-Chat BART (TextBox 2.0) BLEU-1 49.581 #1 of 1 Archive leaderboard report
Dialogue Persona-Chat BART (TextBox 2.0) BLEU-2 39.24 #1 of 1 Archive leaderboard report
Dialogue Persona-Chat BART (TextBox 2.0) Distinct-1 1.44 #1 of 1 Archive leaderboard report
Dialogue Persona-Chat BART (TextBox 2.0) Distinct-2 8.89 #1 of 1 Archive leaderboard report
Machine Translation WMT2016 English-Romanian BART (TextBox 2.0) BLEU-4 37.2 #21 of 21 Archive leaderboard report
Machine Translation WMT2016 Romanian-English BART (TextBox 2.0) BLEU-4 37.48 #21 of 21 Archive leaderboard report
Question Answering SQuAD1.1 BART (TextBox 2.0) Exact Match 86.44 #209 of 213 Archive leaderboard report
Question Answering SQuAD1.1 BART (TextBox 2.0) F1 93.04 #209 of 213 Archive leaderboard report
Question Generation SQuAD1.1 BART (TextBox 2.0) BLEU-4 25.08 #2 of 13 Archive leaderboard report
Question Generation SQuAD1.1 BART (TextBox 2.0) METEOR 26.73 #2 of 13 Archive leaderboard report
Question Generation SQuAD1.1 BART (TextBox 2.0) ROUGE-L 52.55 #2 of 13 Archive leaderboard report
Story Generation WritingPrompts BART (TextBox 2.0) BLEU-1 33.79 #1 of 1 Archive leaderboard report
Story Generation WritingPrompts BART (TextBox 2.0) BLEU-2 15.78 #1 of 1 Archive leaderboard report
Story Generation WritingPrompts BART (TextBox 2.0) Distinct-4 78.762 #1 of 1 Archive leaderboard report
Style Transfer GYAFC BART (TextBox 2.0) Accuracy 94.37 #1 of 1 Archive leaderboard report
Style Transfer GYAFC BART (TextBox 2.0) BLEU-4 76.93 #1 of 1 Archive leaderboard report
Style Transfer GYAFC BART (TextBox 2.0) Harmonic mean 84.74 #1 of 1 Archive leaderboard report
Task-Oriented Dialogue Systems MULTIWOZ 2.0 BART (TextBox 2.0) BLEU-4 20.17 #1 of 1 Archive leaderboard report
Task-Oriented Dialogue Systems MULTIWOZ 2.0 BART (TextBox 2.0) Score 100.07 #1 of 1 Archive leaderboard report
Text Generation ADGEN BART (TextBox 2.0) BLEU-4 10.2 #1 of 1 Archive leaderboard report
Text Generation CSL BART (TextBox 2.0) ROUGE-L 64.34 #1 of 1 Archive leaderboard report
Text Generation CommonGen BART (TextBox 2.0) BLEU-4 28.18 #2 of 4 Archive leaderboard report
Text Generation CommonGen BART (TextBox 2.0) CIDEr 12.98 #2 of 4 Archive leaderboard report
Text Generation CommonGen BART (TextBox 2.0) SPICE 33 #2 of 4 Archive leaderboard report
Text Generation LCSTS BART (TextBox 2.0) ROUGE-L 42.96 #1 of 1 Archive leaderboard report
Text Simplification Wiki-Auto + Turk BART (TextBox 2.0) BLEU-4 90.81 #1 of 1 Archive leaderboard report
Text Simplification Wiki-Auto + Turk BART (TextBox 2.0) METEOR 57.58 #1 of 1 Archive leaderboard report
Text Simplification Wiki-Auto + Turk BART (TextBox 2.0) ROUGE-2 83.36 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections