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 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="2308.08973")

Code

Syntology Ran 10 of 13 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Alab-NII/2wikimultihop officialmentioned in papermentioned on GitHubpytorch report
canghongjian/beam_retriever officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
ShayekhBinIslam/openrag mentioned on GitHubpytorch 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

13 samples harvested; 10 ran; 0 honoured the contract we drafted; 3 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
9ran
3unverified

Licence: 0 of the 13 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 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. “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.

calculate_em_f1 canghongjian/beam_retriever/train_beam_retriever.py official repository ran fingerprinted Apache-2.0 (permissive) · 14b4dc86a2f9d5fe · report
collate_fn canghongjian/beam_retriever/retrieval/datasets.py official repository ran Apache-2.0 (permissive) · 623c2ebe4e288e5d · report
collate_fn_each_hop canghongjian/beam_retriever/retrieval/datasets.py official repository ran Apache-2.0 (permissive) · 385a19954a28f7ad · report
compute_exact canghongjian/beam_retriever/train_reader.py official repository ran fingerprinted Apache-2.0 (permissive) · c1478415449411ed · report
get_next canghongjian/beam_retriever/qa/datasets.py official repository ran fingerprinted Apache-2.0 (permissive) · 13a7774be41bd187 · report
get_tokens canghongjian/beam_retriever/gpt_turbo_exp.py official repository ran fingerprinted Apache-2.0 (permissive) · 8a4f13df2795176e · report
kmp canghongjian/beam_retriever/qa/datasets.py official repository ran fingerprinted Apache-2.0 (permissive) · e142253af9285485 · report
load_saved canghongjian/beam_retriever/utils/utils.py official repository ran Apache-2.0 (permissive) · 69c2c7b48e030046 · report
move_to_cuda canghongjian/beam_retriever/utils/utils.py official repository ran Apache-2.0 (permissive) · a4978f078a7eb7ec · report
normalize_answer canghongjian/beam_retriever/gpt_turbo_exp.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · dae7ab386661a4f4 · report
get_response canghongjian/beam_retriever/llm_exp_long.py official repository unverified Apache-2.0 (permissive) · 0a8f1af973c82ca0 · report
gpt_turbo_request canghongjian/beam_retriever/gpt_turbo_exp.py official repository unverified Apache-2.0 (permissive) · 8e84eac6133f306f · report
reader_mhop_collate canghongjian/beam_retriever/qa/datasets.py official repository 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