Papers › Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner

18 May 2022Findings (NAACL) 2022 7arXiv:2205.09224archive 2025-07-28

Danilo Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henry Zhu, Xinchi Chen, Zhiheng Huang, Peng Xu, Andrew Arnold, Dan Roth

Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way to explain and inspect a QA system's answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. The IRGR model iteratively searches for suitable premises, constructing a single entailment step at a time. Contrary to previous approaches, our method combines generation steps and retrieval of premises, allowing the model to leverage intermediate conclusions, and mitigating the input size limit of baseline encoder-decoder models. We conduct experiments using the EntailmentBank dataset, where we outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300% gain in overall correctness.

PaperPDFConference PDFCodeCode 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="2205.09224")

Code

Syntology Ran 2 of 19 code samples harvested from 1 repository linked to this paper; 17 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

amazon-research/irgr officialmentioned in paperpytorchApache-2.0 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

19 samples harvested; 2 ran; 0 honoured the contract we drafted; 17 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 · our draft was wrong
1ran
17unverified

Licence: 0 of the 19 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 amazon-research/irgr. “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.

replace_punctuation amazon-research/irgr/src/entailment_bank/utils/eval_utils.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d2166ef001a9e416 · report
trim_batch amazon-research/irgr/src/entailment_bank/utils/angle_utils.py official repository ran Apache-2.0 (permissive) · eeb8dc60c6ef1fa4 · report
convert_datapoint_to_sent_to_text amazon-research/irgr/src/retrieval_utils.py official repository unverified Apache-2.0 (permissive) · 74453f96447f48f6 · report
count_phrase_matches amazon-research/irgr/src/entailment_bank/utils/entail_trees_utils.py official repository unverified Apache-2.0 (permissive) · 44b66cb0347665db · report
create_sentence_uuid_map_from_corpus amazon-research/irgr/src/retrieval_utils.py official repository unverified Apache-2.0 (permissive) · 42c325aaed66dd65 · report
encode_line amazon-research/irgr/src/entailment_bank/utils/angle_utils.py official repository unverified Apache-2.0 (permissive) · ab5d9464aeabf9fd · report
get_results_file_path amazon-research/irgr/src/base_utils.py official repository unverified Apache-2.0 (permissive) · cf21a7d00a46e668 · report
load_jsonl amazon-research/irgr/src/entailment_bank/utils/angle_utils.py official repository unverified Apache-2.0 (permissive) · c30d329a797e15bd · report
load_slot_data_by_id amazon-research/irgr/src/entailment_bank/utils/eval_utils.py official repository unverified Apache-2.0 (permissive) · 51014481762b0d1b · report
parse_lisp amazon-research/irgr/src/entailment_bank/utils/proof_utils.py official repository unverified Apache-2.0 (permissive) · 970c22892bfbf76b · report
parse_lisp_tokens amazon-research/irgr/src/entailment_bank/utils/proof_utils.py official repository unverified Apache-2.0 (permissive) · af3e6075f5840574 · report
recursive_polish_notation amazon-research/irgr/src/entailment_bank/utils/proof_utils.py official repository unverified Apache-2.0 (permissive) · b015b685dfa43094 · report
run_funtion_redirect_stdout amazon-research/irgr/src/base_utils.py official repository unverified Apache-2.0 (permissive) · de7e75f07bfecdb0 · report
score_string_similarity amazon-research/irgr/src/entailment_bank/utils/eval_utils.py official repository unverified Apache-2.0 (permissive) · 00139853f0c3a89e · report
sent_text_as_counter amazon-research/irgr/src/retrieval_utils.py official repository unverified Apache-2.0 (permissive) · 68ef7c2586529325 · report
sentence_index amazon-research/irgr/src/entailment_bank/utils/entail_trees_utils.py official repository unverified Apache-2.0 (permissive) · 8f025f3f4d630f9a · report
sort_sentence_ids_match amazon-research/irgr/src/entailment_bank/utils/entail_trees_utils.py official repository unverified Apache-2.0 (permissive) · bc66cae80c3a0886 · report
split_info_sentences amazon-research/irgr/src/entailment_bank/eval/run_scorer.py official repository unverified Apache-2.0 (permissive) · 110b38cab88d9900 · report
str_replace_single_pass amazon-research/irgr/src/base_utils.py official repository unverified Apache-2.0 (permissive) · fff8963152d95bfe · report

Tasks

DecoderQuestion AnsweringRetrieval

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