Papers › ReasonBERT: Pre-trained to Reason with Distant Supervision

ReasonBERT: Pre-trained to Reason with Distant Supervision

10 Sep 2021EMNLP 2021 11arXiv:2109.04912archive 2025-07-28

Xiang Deng, Yu Su, Alyssa Lees, You Wu, Cong Yu, Huan Sun

We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals from local contexts of naturally occurring texts, we propose a generalized notion of distant supervision to automatically connect multiple pieces of text and tables to create pre-training examples that require long-range reasoning. Different types of reasoning are simulated, including intersecting multiple pieces of evidence, bridging from one piece of evidence to another, and detecting unanswerable cases. We conduct a comprehensive evaluation on a variety of extractive question answering datasets ranging from single-hop to multi-hop and from text-only to table-only to hybrid that require various reasoning capabilities and show that ReasonBert achieves remarkable improvement over an array of strong baselines. Few-shot experiments further demonstrate that our pre-training method substantially improves sample efficiency.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2109.04912")

Code

Syntology Ran 3 of 11 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong.

By repository: official repository: 11 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sunlab-osu/reasonbert officialmentioned in papermentioned on GitHubpytorchApache-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

11 samples harvested; 3 ran; 1 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
8unverified

Licence: 0 of the 11 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 sunlab-osu/reasonbert. “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.

exact_match_score sunlab-osu/reasonbert/model/metric.py official repository ran · violated contract Apache-2.0 (permissive) · f6c275d6a18330a9 · report
f1_score sunlab-osu/reasonbert/model/metric.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · fdd9a4d20f5a9d6f · report
normalize_answer sunlab-osu/reasonbert/model/metric.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c6a80c065d2e4851 · report
MRQA_preprocess sunlab-osu/reasonbert/data_loader/data_loaders.py official repository unverified Apache-2.0 (permissive) · ac2fa2763f9ff92e · report
cross_entropy_with_onehot sunlab-osu/reasonbert/model/model.py official repository unverified Apache-2.0 (permissive) · 46aaba4ebd9f132b · report
flatten sunlab-osu/reasonbert/data_loader/tapas_modelling.py official repository unverified Apache-2.0 (permissive) · c2c2e8507e9edd19 · report
gather sunlab-osu/reasonbert/data_loader/tapas_modelling.py official repository unverified Apache-2.0 (permissive) · ead963170369d948 · report
get_linear_schedule_with_warmup sunlab-osu/reasonbert/model/loss.py official repository unverified Apache-2.0 (permissive) · afba2c06a42074fe · report
get_tokenized_loc sunlab-osu/reasonbert/data_loader/data_loaders.py official repository unverified Apache-2.0 (permissive) · 8c5fc643936371bd · report
nll_loss sunlab-osu/reasonbert/model/loss.py official repository unverified Apache-2.0 (permissive) · 8c2db3d4435816c0 · report
tmp_func sunlab-osu/reasonbert/data_loader/data_loaders.py official repository unverified Apache-2.0 (permissive) · dd644affb7c645e2 · report

Tasks

Extractive Question-AnsweringQuestion AnsweringSemantic Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering TriviaQA ReasonBERTR F1 45.5 #55 of 56 Archive leaderboard report
Question Answering TriviaQA ReasonBERTB F1 37.2 #56 of 56 Archive leaderboard report
Semantic Parsing GraphQuestions ReasonBERTR F1 Score 41.3 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: ReasonBERT

ReasonBERT

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