Papers › Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and...

Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning

12 Oct 2020EMNLP 2020 11arXiv:2010.05906archive 2025-07-28

Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena Hwang, Ronan Le Bras, Antoine Bosselut, Yejin Choi

Abductive and counterfactual reasoning, core abilities of everyday human cognition, require reasoning about what might have happened at time t, while conditioning on multiple contexts from the relative past and future. However, simultaneous incorporation of past and future contexts using generative language models (LMs) can be challenging, as they are trained either to condition only on the past context or to perform narrowly scoped text-infilling. In this paper, we propose DeLorean, a new unsupervised decoding algorithm that can flexibly incorporate both the past and future contexts using only off-the-shelf, left-to-right language models and no supervision. The key intuition of our algorithm is incorporating the future through back-propagation, during which, we only update the internal representation of the output while fixing the model parameters. By alternating between forward and backward propagation, DeLorean can decode the output representation that reflects both the left and right contexts. We demonstrate that our approach is general and applicable to two nonmonotonic reasoning tasks: abductive text generation and counterfactual story revision, where DeLorean outperforms a range of unsupervised and some supervised methods, based on automatic and human evaluation.

PaperPDFConference PDFCodeCode 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 8 code samples: 7 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 8: 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) · 3 unverified. Where Syntology's instrument failed: 5 where the contract check could not run; 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: 7 samples from 1 repository, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qkaren/unsup_gen_for_cms_reasoning officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 4 ran (4 instrument-failed) · 3 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

8 samples harvested: 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) · 3 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.

5ran; the contract check could not run
3unverified

Licence: 8 of the 8 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 qkaren/unsup_gen_for_cms_reasoning. 1 sample is listed last, in a group without a repository. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

qkaren/unsup_gen_for_cms_reasoning official repository 7 samples, 4 ran (4 instrument-failed) · 3 unverified
forward_pass in 9 papers abductive_main.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ddba0eea3fb589d6 · report fixture: signature logits:Tensor/3/float, model:callable/0/?, tokenizer:StandInTokenizer/0/?, o1_logits:Tensor/3/float, o1:Tensor/2/int, length:int/0/int, max_length:int/0/int, mix_rate:float/0/float, temperature:float/0/float, top_k:int/0/int, device:str/0/str, verbose:bool/0/bool · returned tuple · level recorded 2026-09-22
get_text_from_logits abductive_main.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 468a8782c34e522c · report fixture: signature logits:Tensor/3/float, tokenizer:MinimalTokenizer/0/?, temperature:float/0/float, top_k:int/0/int · returned str · level recorded 2026-09-24
get_token_from_logits abductive_main.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · c7967a9cb34c0871 · report fixture: signature logits:Tensor/2/float, temperature:float/0/float, top_k:int/0/int · returned Tensor · level recorded 2026-09-22
top_k_filter in 9 papers abductive_main.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 66bb73836d7e23ad · report fixture: signature logits:Tensor/2/float, k:int/0/int, probs:bool/0/bool, device:str/0/str · returned Tensor · level recorded 2026-09-22
backward_pass abductive_main.py unverified no licence file found · pointer only · 5f648876b576f47b · report
delorean_decoding abductive_main.py unverified no licence file found · pointer only · 5a36862dd43da237 · report
get_input_embeds abductive_main.py unverified no licence file found · pointer only · e8feea2d968e86f6 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
to_var in 51 papers
census: 12 implementations from 21 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · bbebd95a156061b0 · report fixture: signature x:Tensor/2/float, requires_grad:bool/0/bool, volatile:bool/0/bool, device:str/0/str · returned Tensor · level recorded 2026-09-22

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 DELOREAN (graph method: DELOREAN). 8 bricks; individually on a fixture: 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) · 3 unverified. The assembly has not been run end-to-end.

  1. delorean_decoding entry · level 0 · unverified · 5a36862dd43da237
  2. backward_pass update_rule · level 0 · unverified · 5f648876b576f47b
  3. forward_pass model · level 1 · ran; the contract check could not run (RAISES) · ddba0eea3fb589d6
  4. get_input_embeds helper · level 0 · unverified · e8feea2d968e86f6
  5. get_text_from_logits helper · level 1 · ran; the contract check could not run (RAISES) · 468a8782c34e522c
  6. to_var helper · level 1 · ran; the contract check could not run (RAISES) · bbebd95a156061b0
  7. get_token_from_logits sampler · level 1 · ran; the contract check could not run (RAISES) · c7967a9cb34c0871
  8. top_k_filter helper · level 1 · ran; the contract check could not run (RAISES) · 66bb73836d7e23ad

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="2010.05906") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Counterfactual ReasoningText GenerationText Infilling

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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