Papers › Abductive Commonsense Reasoning

Abductive Commonsense Reasoning

15 Aug 2019ICLR 2020 1arXiv:1908.05739archive 2025-07-28

Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Scott Wen-tau Yih, Yejin Choi

Abductive reasoning is inference to the most plausible explanation. For example, if Jenny finds her house in a mess when she returns from work, and remembers that she left a window open, she can hypothesize that a thief broke into her house and caused the mess, as the most plausible explanation. While abduction has long been considered to be at the core of how people interpret and read between the lines in natural language (Hobbs et al., 1988), there has been relatively little research in support of abductive natural language inference and generation. We present the first study that investigates the viability of language-based abductive reasoning. We introduce a challenge dataset, ART, that consists of over 20k commonsense narrative contexts and 200k explanations. Based on this dataset, we conceptualize two new tasks -- (i) Abductive NLI: a multiple-choice question answering task for choosing the more likely explanation, and (ii) Abductive NLG: a conditional generation task for explaining given observations in natural language. On Abductive NLI, the best model achieves 68.9% accuracy, well below human performance of 91.4%. On Abductive NLG, the current best language generators struggle even more, as they lack reasoning capabilities that are trivial for humans. Our analysis leads to new insights into the types of reasoning that deep pre-trained language models fail to perform--despite their strong performance on the related but more narrowly defined task of entailment NLI--pointing to interesting avenues for future research.

PaperPDFConference PDFCodeCode Syntology ran

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 15 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 2 repositories, 14 ran (11 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

allenai/abductive-commonsense-reasoning mentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report
seungonekim/abductive-commonsense-reasoning mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 6 ran (3 instrument-failed) · 0 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

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
11ran
1unverified

Licence: 2 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

allenai/abductive-commonsense-reasoning community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
correct_middle anli/corpus_statistics.py ran Apache-2.0 (permissive) · 0b75dd17295eeef5 · report fixture: signature r:dict/0/? · returned int · level recorded 2026-09-24
incorrect_middle anli/corpus_statistics.py ran Apache-2.0 (permissive) · d0d6da0d2a941144 · report fixture: signature r:dict/0/? · returned str · level recorded 2026-09-24
mean_word_lens anli/corpus_statistics.py ran Apache-2.0 (permissive) · a0397d9919a23e00 · report fixture: signature lst:list/1/str · returned float64 · level recorded 2026-09-24
num_correct anli/run_anli.py ran Apache-2.0 (permissive) · aebac6962806ff28 · report fixture: signature out:ndarray/2/float, labels:ndarray/1/int · returned int64 · level recorded 2026-09-24
read_jsonl_lines in 5 papers utils/file_utils.py ran Apache-2.0 (permissive) · d0d8b8a41cf48c5e · report fixture: signature input_file:str/0/str · returned list · level recorded 2026-09-24
read_lines in 19 papers utils/file_utils.py ran Apache-2.0 (permissive) · 7e775841119597bd · report fixture: signature input_file:str/0/str · returned list · level recorded 2026-09-24
sample_sequence in 8 papers anlg/run_generation.py ran Apache-2.0 (permissive) · e2f5996137ac1cb9 · report fixture: signature model:callable/0/?, length:int/0/int, context:list/1/int, num_samples:int/0/int, temperature:float/0/float, top_k:int/0/int, top_p:float/0/float, is_xlnet:bool/0/bool, device:str/0/str, comet_input:NoneType/0/?, comet_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
anlg/run_generation.py ran Apache-2.0 (permissive) · ee8b235cc453809b · report fixture: signature logits:Tensor/1/float, top_k:int/0/int, top_p:float/0/float, filter_value:float/0/float · returned Tensor · level recorded 2026-09-25
select_field in 12 papers anli/data_processors.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 0a546b305d274996 · report
seungonekim/abductive-commonsense-reasoning community (archive-listed) 6 samples, 6 ran (3 instrument-failed) · 0 unverified
bert_encode anlg/evaluation/bert_score/utils.py ran Apache-2.0 (permissive) · 8f0d52f285c5001f · report fixture: signature model:callable/0/?, x:Tensor/2/int, attention_mask:Tensor/2/int · returned Tensor · level recorded 2026-09-24
cook_refs in 36 papers anlg/evaluation/bleu/bleu_scorer.py ran · our draft was wrong Apache-2.0 (permissive) · 7586e1d32f7325f7 · report fixture: signature refs:list/1/str, eff:str/0/str, n:int/0/int · returned tuple · level recorded 2026-09-25
cook_test in 35 papers anlg/evaluation/bleu/bleu_scorer.py ran Apache-2.0 (permissive) · 9c09fbe68477f787 · report fixture: signature test:str/0/str, tup:tuple/1/int, eff:NoneType/0/?, n:int/0/int · returned dict · level recorded 2026-09-24
padding in 37 papers anlg/evaluation/bert_score/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 13ef8eeae8570519 · report fixture: signature arr:list/1/list, pad_token:int/0/int, dtype:dtype/0/? · returned tuple · level recorded 2026-09-22
precook in 38 papers anlg/evaluation/bleu/bleu_scorer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ec4448373d72d636 · report fixture: signature s:str/0/str, n:int/0/int, out:bool/0/bool · returned tuple · level recorded 2026-09-22
process in 60 papers anlg/evaluation/bert_score/utils.py ran Apache-2.0 (permissive) · 94931df06dab4db5 · report fixture: signature a:str/0/str, tokenizer:StandInTokenizer/0/? · returned set · level recorded 2026-09-24

Tasks

Multiple-choiceNatural Language InferenceQuestion Answering

Datasets

Introduced by this paper, per the archive.

ART Dataset

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