Papers › Explaining Answers with Entailment Trees

Explaining Answers with Entailment Trees

17 Apr 2021EMNLP 2021 11arXiv:2104.08661archive 2025-07-28

Bhavana Dalvi, Peter Jansen, Oyvind Tafjord, Zhengnan Xie, Hannah Smith, Leighanna Pipatanangkura, Peter Clark

Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If this could be done, new opportunities for understanding and debugging the system's reasoning become possible. Our approach is to generate explanations in the form of entailment trees, namely a tree of multipremise entailment steps from facts that are known, through intermediate conclusions, to the hypothesis of interest (namely the question + answer). To train a model with this skill, we created ENTAILMENTBANK, the first dataset to contain multistep entailment trees. Given a hypothesis (question + answer), we define three increasingly difficult explanation tasks: generate a valid entailment tree given (a) all relevant sentences (b) all relevant and some irrelevant sentences, or (c) a corpus. We show that a strong language model can partially solve these tasks, in particular when the relevant sentences are included in the input (e.g., 35% of trees for (a) are perfect), and with indications of generalization to other domains. This work is significant as it provides a new type of dataset (multistep entailments) and baselines, offering a new avenue for the community to generate richer, more systematic explanations.

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 17 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 1 repository, 16 ran (14 with no instrument failure; 2 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

allenai/entailment_bank mentioned on GitHubApache-2.0Syntology: 17 samples, 16 ran (2 instrument-failed) · 1 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

17 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 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.

2ran · our draft was wrong
14ran
1unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 allenai/entailment_bank. “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.

allenai/entailment_bank community (archive-listed) 17 samples, 16 ran (2 instrument-failed) · 1 unverified
count_phrase_matches utils/entail_trees_utils.py ran fingerprinted Apache-2.0 (permissive) · 44b66cb0347665db · report fixture: signature phrase:str/0/str, reference:str/0/str · returned int · level recorded 2026-09-24
decompose_slots utils/nlp_agent.py ran Apache-2.0 (permissive) · a09d8995568f8d93 · report fixture: signature string:str/0/str, fmt:NoneType/0/? · returned dict · level recorded 2026-09-24
load_jsonl in 179 papers utils/angle_utils.py ran Apache-2.0 (permissive) · c30d329a797e15bd · report fixture: signature file_name:str/0/str · returned list · level recorded 2026-09-24
load_slot_data_by_id utils/eval_utils.py ran Apache-2.0 (permissive) · 51014481762b0d1b · report fixture: signature slot_file:str/0/str · returned dict · level recorded 2026-09-24
make_predslot_record eval/run_scorer_task3.py ran Apache-2.0 (permissive) · 213992abc08e4d79 · report fixture: signature pred:dict/0/?, hypothesis:str/0/str · returned dict · level recorded 2026-09-24
new_dict_update utils/nlp_agent.py ran Apache-2.0 (permissive) · baf18760bfe228c7 · report fixture: signature old_dict:dict/0/?, update_dict:dict/0/? · returned dict · level recorded 2026-09-24
parse_lisp utils/proof_utils.py ran Apache-2.0 (permissive) · 970c22892bfbf76b · report fixture: signature input_string:str/0/str, token_map:NoneType/0/? · returned list · level recorded 2026-09-24
parse_lisp_tokens utils/proof_utils.py ran fingerprinted Apache-2.0 (permissive) · af3e6075f5840574 · report fixture: signature tokens:list/1/str · returned list · level recorded 2026-09-24
recursive_polish_notation utils/proof_utils.py ran Apache-2.0 (permissive) · b015b685dfa43094 · report fixture: signature proof_list:list/1/str · returned list · level recorded 2026-09-24
replace_punctuation in 5 papers utils/eval_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d2166ef001a9e416 · report fixture: signature str:str/0/str · returned str · level recorded 2026-09-22
score_string_similarity in 5 papers utils/eval_utils.py ran fingerprinted Apache-2.0 (permissive) · 00139853f0c3a89e · report fixture: signature str1:str/0/str, str2:str/0/str · returned float · level recorded 2026-09-24
sentence_index utils/entail_trees_utils.py ran Apache-2.0 (permissive) · 8f025f3f4d630f9a · report fixture: signature sentence_id:str/0/str · returned int · level recorded 2026-09-24
sort_sentence_ids_match utils/entail_trees_utils.py ran Apache-2.0 (permissive) · bc66cae80c3a0886 · report fixture: signature match:MockMatch/0/? · returned str · level recorded 2026-09-24
split_info_sentences eval/run_scorer.py ran fingerprinted Apache-2.0 (permissive) · 110b38cab88d9900 · report fixture: signature context:str/0/str · returned dict · level recorded 2026-09-24
split_mcoptions utils/nlp_agent.py ran fingerprinted Apache-2.0 (permissive) · 6cfa0a08a9e5f18a · report fixture: signature mcoptions:str/0/str · returned tuple · level recorded 2026-09-24
trim_batch in 13 papers utils/angle_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · eeb8dc60c6ef1fa4 · report fixture: signature input_ids:Tensor/2/int, pad_token_id:int/0/int, attention_mask:Tensor/2/int · returned tuple · level recorded 2026-09-24
encode_line in 7 papers utils/angle_utils.py unverified Apache-2.0 (permissive) · ab5d9464aeabf9fd · report

Tasks

Language ModellingQuestion Answering

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

EntailmentBank

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