Papers › End-to-End Beam Retrieval for Multi-Hop Question Answering

End-to-End Beam Retrieval for Multi-Hop Question Answering

17 Aug 2023arXiv:2308.08973archive 2025-07-28

Jiahao Zhang, Haiyang Zhang, Dongmei Zhang, Yong liu, Shen Huang

Multi-hop question answering (QA) involves finding multiple relevant passages and step-by-step reasoning to answer complex questions, indicating a retrieve-and-read paradigm. However, previous retrievers were customized for two-hop questions, and most of them were trained separately across different hops, resulting in a lack of supervision over the entire multi-hop retrieval process and leading to poor performance in complicated scenarios beyond two hops. In this work, we introduce Beam Retrieval, an end-to-end beam retrieval framework for multi-hop QA. This approach models the multi-hop retrieval process in an end-to-end manner by jointly optimizing an encoder and two classification heads across all hops. Moreover, Beam Retrieval maintains multiple partial hypotheses of relevant passages at each step, expanding the search space and reducing the risk of missing relevant passages. To establish a complete QA system, we incorporate a supervised reader or a large language model (LLM). Experimental results demonstrate that Beam Retrieval achieves a nearly 50% improvement compared with baselines on challenging MuSiQue-Ans, and it also surpasses all previous retrievers on HotpotQA and achieves 99.9% precision on 2WikiMultiHopQA. Providing high-quality context, Beam Retrieval helps our supervised reader achieve new state-of-the-art performance and substantially improves the few-shot QA performance of LLMs.

PaperPDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (9 with no instrument failure; 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

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.

Alab-NII/2wikimultihop officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps (arXiv:2011.01060; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
canghongjian/beam_retriever officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 10 ran (1 instrument-failed) · 3 unverified report
ShayekhBinIslam/openrag mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection (arXiv:2310.11511; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures 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.

1ran · our draft was wrong
9ran
3unverified

Licence: 2 of the 13 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 canghongjian/beam_retriever. “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.

canghongjian/beam_retriever official repository 13 samples, 10 ran (1 instrument-failed) · 3 unverified
calculate_em_f1 train_beam_retriever.py ran fingerprinted Apache-2.0 (permissive) · 14b4dc86a2f9d5fe · report fixture: signature predicted_support_idxs:list/1/int, gold_support_idxs:list/1/int · returned tuple · level recorded 2026-09-24
collate_fn in 500 papers retrieval/datasets.py ran Apache-2.0 (permissive) · 623c2ebe4e288e5d · report fixture: signature samples:list/1/dict · returned dict · level recorded 2026-09-24
collate_fn_each_hop retrieval/datasets.py ran Apache-2.0 (permissive) · 385a19954a28f7ad · report fixture: signature samples:list/1/dict · returned dict · level recorded 2026-09-24
compute_exact in 17 papers train_reader.py ran fingerprinted Apache-2.0 (permissive) · c1478415449411ed · report fixture: signature a_gold:str/0/str, a_pred:str/0/str · returned int · level recorded 2026-09-24
get_next qa/datasets.py ran fingerprinted Apache-2.0 (permissive) · 13a7774be41bd187 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-24
get_tokens in 40 papers gpt_turbo_exp.py ran fingerprinted Apache-2.0 (permissive) · 8a4f13df2795176e · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-24
kmp qa/datasets.py ran fingerprinted Apache-2.0 (permissive) · e142253af9285485 · report fixture: signature src:str/0/str, tgt:str/0/str · returned int · level recorded 2026-09-24
load_saved utils/utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 69c2c7b48e030046 · report fixture: signature model:callable/0/?, path:str/0/str, exact:bool/0/bool · returned SimpleModel · level recorded 2026-09-24
move_to_cuda in 22 papers utils/utils.py ran Apache-2.0 (permissive) · a4978f078a7eb7ec · report fixture: signature sample:dict/0/? · returned dict · level recorded 2026-09-24
normalize_answer in 304 papers gpt_turbo_exp.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · dae7ab386661a4f4 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
get_response in 48 papers llm_exp_long.py unverified Apache-2.0 (permissive) · 0a8f1af973c82ca0 · report
gpt_turbo_request gpt_turbo_exp.py unverified Apache-2.0 (permissive) · 8e84eac6133f306f · report
reader_mhop_collate qa/datasets.py unverified Apache-2.0 (permissive) · 0918ce50e5647e35 · report

Tasks

Language ModellingLarge Language ModelMulti-hop Question AnsweringQuestion AnsweringRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-hop Question Answering MuSiQue-Ans Beam Retrieval An 69.2 #1 of 1 Archive leaderboard report
Multi-hop Question Answering MuSiQue-Ans Beam Retrieval Sp 91.4 #1 of 1 Archive leaderboard report
Question Answering HotpotQA Beam Retrieval ANS-EM 0.727 #1 of 72 Archive leaderboard report
Question Answering HotpotQA Beam Retrieval ANS-F1 0.850 #1 of 72 Archive leaderboard report
Question Answering HotpotQA Beam Retrieval JOINT-EM 0.505 #1 of 72 Archive leaderboard report
Question Answering HotpotQA Beam Retrieval JOINT-F1 0.775 #1 of 72 Archive leaderboard report
Question Answering HotpotQA Beam Retrieval SUP-EM 0.663 #1 of 72 Archive leaderboard report
Question Answering HotpotQA Beam Retrieval SUP-F1 0.901 #1 of 72 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

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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