Papers › LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference

LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference

18 May 2025arXiv:2505.12260archive 2025-07-28

Guangyuan Ma, Yongliang Ma, Xuanrui Gou, Zhenpeng Su, Ming Zhou, Songlin Hu

Large Language Models (LLMs)-based hybrid retrieval uses LLMs to encode queries and documents into low-dimensional dense or high-dimensional sparse vectors. It retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query encoder. Although LLMs significantly enhance retrieval capabilities, serving deeply parameterized LLMs slows down query inference throughput and increases demands for online deployment resources. In this paper, we propose LightRetriever, a novel LLM-based hybrid retriever with extremely lightweight query encoders. Our method retains a full-sized LLM for document encoding, but reduces the workload of query encoding to no more than an embedding lookup. Compared to serving a full-sized LLM on an H800 GPU, our approach achieves over a 1000x speedup for query inference with GPU acceleration, and even a 20x speedup without GPU. Experiments on large-scale retrieval benchmarks demonstrate that our method generalizes well across diverse retrieval tasks, retaining an average of 95% full-sized performance.

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="2505.12260")

Code

Syntology Ran 2 of 11 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 11 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.

caskcsg/lightretriever 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

11 samples harvested; 2 ran; 0 honoured the contract we drafted; 9 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
9unverified

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 caskcsg/lightretriever. “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.

dcg_score caskcsg/lightretriever/src/lightretriever/finetune/metrics.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 43e79e8e0904d5d8 · report
ndcg_score caskcsg/lightretriever/src/lightretriever/finetune/metrics.py official repository ran Apache-2.0 (permissive) · aaa4cece9f41ea15 · report
find_closest_power_of_2 caskcsg/lightretriever/src/lightretriever/trainer.py official repository unverified Apache-2.0 (permissive) · 97574ff51cffea4e · report
get_cosine_schedule_with_warmup_minlr caskcsg/lightretriever/src/lightretriever/scheduler.py official repository unverified Apache-2.0 (permissive) · d091bfa8194ca89f · report
get_linear_schedule_with_warmup_minlr caskcsg/lightretriever/src/lightretriever/scheduler.py official repository unverified Apache-2.0 (permissive) · 9aaa2ddc83faa93d · report
get_lm_head caskcsg/lightretriever/src/lightretriever/finetune/modeling_hybrid.py official repository unverified Apache-2.0 (permissive) · 8795573bc2983705 · report
get_reg_weight_scaling_factor caskcsg/lightretriever/src/lightretriever/scheduler.py official repository unverified Apache-2.0 (permissive) · 7ec8ad33274123d1 · report
mean_eos_pooling caskcsg/lightretriever/src/lightretriever/finetune/dense_pooling.py official repository unverified Apache-2.0 (permissive) · cd3a8d8e0d35ed6b · report
mrr_score caskcsg/lightretriever/src/lightretriever/finetune/metrics.py official repository unverified Apache-2.0 (permissive) · c1933bf46ff5c9b6 · report
pooling caskcsg/lightretriever/src/lightretriever/finetune/dense_pooling.py official repository unverified Apache-2.0 (permissive) · 028d8766e22f9773 · report
rewrite_logs caskcsg/lightretriever/src/lightretriever/trainer.py official repository unverified Apache-2.0 (permissive) · d14a93abddd46c17 · report

Tasks

Retrieval

1 archive task tag without a task page not shown.

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