Papers › Generating EDU Extracts for Plan-Guided Summary Re-Ranking

Generating EDU Extracts for Plan-Guided Summary Re-Ranking

28 May 2023arXiv:2305.17779archive 2025-07-28

Griffin Adams, Alexander R. Fabbri, Faisal Ladhak, Kathleen McKeown, Noémie Elhadad

Two-step approaches, in which summary candidates are generated-then-reranked to return a single summary, can improve ROUGE scores over the standard single-step approach. Yet, standard decoding methods (i.e., beam search, nucleus sampling, and diverse beam search) produce candidates with redundant, and often low quality, content. In this paper, we design a novel method to generate candidates for re-ranking that addresses these issues. We ground each candidate abstract on its own unique content plan and generate distinct plan-guided abstracts using a model's top beam. More concretely, a standard language model (a BART LM) auto-regressively generates elemental discourse unit (EDU) content plans with an extractive copy mechanism. The top K beams from the content plan generator are then used to guide a separate LM, which produces a single abstractive candidate for each distinct plan. We apply an existing re-ranker (BRIO) to abstractive candidates generated from our method, as well as baseline decoding methods. We show large relevance improvements over previously published methods on widely used single document news article corpora, with ROUGE-2 F1 gains of 0.88, 2.01, and 0.38 on CNN / Dailymail, NYT, and Xsum, respectively. A human evaluation on CNN / DM validates these results. Similarly, on 1k samples from CNN / DM, we show that prompting GPT-3 to follow EDU plans outperforms sampling-based methods by 1.05 ROUGE-2 F1 points. Code to generate and realize plans is available at https://github.com/griff4692/edu-sum.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 6 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; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 6 ran (0 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

griff4692/edu-sum officialmentioned in papermentioned on GitHubjaxSyntology: 10 samples, 6 ran (6 instrument-failed) · 4 unverified 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

10 samples harvested: 6 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; 6 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
4unverified

Licence: 10 of the 10 samples 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 griff4692/edu-sum. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

griff4692/edu-sum official repository 10 samples, 6 ran (6 instrument-failed) · 4 unverified
_get_ngrams model/gen_from_extract.py ran · our draft was wrong no licence file found · pointer only · d0873cb7263347b8 · report fixture: signature n:int/0/int, text:list/1/str · returned set · level recorded 2026-09-22
_get_word_ngrams model/gen_from_extract.py ran · our draft was wrong no licence file found · pointer only · 194b802598abbcbb · report fixture: signature n:int/0/int, sentences:list/1/list · returned set · level recorded 2026-09-22
cal_rouge model/gen_from_extract.py ran · our draft was wrong no licence file found · pointer only · 2498cbc3aebe7442 · report fixture: signature evaluated_ngrams:set/0/?, reference_ngrams:set/0/? · returned dict · level recorded 2026-09-22
compute_implied model/gen_from_extract.py ran · our draft was wrong no licence file found · pointer only · 64ecc872e05c4195 · report fixture: signature args:MockArgs/0/?, nlp:callable/0/?, pred_str:list/1/str, source_annotated:str/0/str · returned list · level recorded 2026-09-22
edus_from_html model/gen_from_extract.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 34dda1ff2147bd09 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-22
filter_out_extract_tags model/gen_from_extract.py ran · our draft was wrong no licence file found · pointer only · d987e6b1911dad9e · report fixture: signature text:str/0/str, keep_idxs:set/0/? · returned str · level recorded 2026-09-22
convert_to_sents model/gen_from_extract.py unverified no licence file found · pointer only · 9be35b5988ecd05d · report
dialogue_to_sents model/gen_from_extract.py unverified no licence file found · pointer only · a9cd10a2e14f3e25 · report
gain_selection model/gen_from_extract.py unverified no licence file found · pointer only · 66d8d1c844a8fc9b · report
gen_from_guide model/gen_from_extract.py unverified no licence file found · pointer only · 956c6de86c9e0856 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for plan-guided summary re-ranking method (graph method: plan-guided summary re-ranking method). 10 bricks; individually on a fixture: 6 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; 6 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. gen_from_guide entry · level 0 · unverified · 956c6de86c9e0856
  2. compute_implied helper · level 1 · ran · our draft was wrong · 64ecc872e05c4195
  3. filter_out_extract_tags helper · level 1 · ran · our draft was wrong · d987e6b1911dad9e
  4. convert_to_sents helper · level 0 · unverified · 9be35b5988ecd05d
  5. edus_from_html helper · level 1 · ran · our draft was wrong · 34dda1ff2147bd09
  6. gain_selection helper · level 0 · unverified · 66d8d1c844a8fc9b
  7. dialogue_to_sents helper · level 0 · unverified · a9cd10a2e14f3e25
  8. _get_word_ngrams helper · level 1 · ran · our draft was wrong · 194b802598abbcbb
  9. cal_rouge helper · level 1 · ran · our draft was wrong · 2498cbc3aebe7442
  10. _get_ngrams helper · level 1 · ran · our draft was wrong · d0873cb7263347b8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2305.17779") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModellingRe-Ranking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBARTBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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