Papers › POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval

25 May 2025arXiv:2505.19189archive 2025-07-28

Yaoyang Liu, Junlin Li, Yinjun Wu, Zhen Chen

Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages one LLM for query decomposition and searches the optimal prompt with an LLM-based optimizer. We further propose an end-to-end training algorithm to alternatively optimize the prompt for query decomposition and the downstream models. This algorithm can achieve superior MVR performance at a reasonable training cost as our theoretical analysis suggests. POQD can be integrated seamlessly into arbitrary retrieval-based systems such as Retrieval-Augmented Generation (RAG) systems. Extensive empirical studies on representative RAG-based QA tasks show that POQD outperforms existing query decomposition strategies in both retrieval performance and end-to-end QA accuracy. POQD is available at https://github.com/PKU-SDS-lab/POQD-ICML25.

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="2505.19189")

Code

Syntology Ran 5 of 5 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 5 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pku-sds-lab/poqd-icml25 officialmentioned in paper 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

5 samples harvested; 5 ran; 3 honoured the contract we drafted; 0 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.

3ran · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it

Licence: 5 of the 5 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 pku-sds-lab/poqd-icml25. “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.

compute_dependency_aware_sim_score pku-sds-lab/poqd-icml25/Decompose_retrieval/dessert_minheap_torch.py official repository ran · fixture could not drive it no licence file found · pointer only · 6a1293cffc850680 · report
dot_scores pku-sds-lab/poqd-icml25/Decompose_retrieval/dessert_minheap_torch.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 781868bd24cd34b6 · report
embed_queries pku-sds-lab/poqd-icml25/Decompose_retrieval/manyqa_utils.py official repository ran · honoured contract no licence file found · pointer only · 164af1d4f47e5f20 · report
embed_queries_ls pku-sds-lab/poqd-icml25/Decompose_retrieval/manyqa_utils.py official repository ran · our draft was wrong no licence file found · pointer only · b3e63a2287c2502f · report
embed_queries_with_input_queries pku-sds-lab/poqd-icml25/Decompose_retrieval/manyqa_utils.py official repository ran · honoured contract no licence file found · pointer only · 5e9ca8db2d431e36 · report

Tasks

Information RetrievalRAGRetrievalRetrieval-augmented Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBARTBERTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionRAGResidual ConnectionSoftmaxWeight DecayWordPiece

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