Papers › RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation

RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation

16 Feb 2025arXiv:2502.10996archive 2025-07-28

Pengcheng Jiang, Lang Cao, Ruike Zhu, Minhao Jiang, Yunyi Zhang, Jimeng Sun, Jiawei Han

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation (RAG) methods provide external information, the lack of explicit organization among retrieved passages limits their effectiveness, leading to brittle reasoning pathways. Recent interpretability studies highlighting the importance of structured intermediate reasoning further align with this perspective. We propose Retrieval-And-Structuring (RAS), a framework that dynamically constructs query-specific knowledge graphs through iterative retrieval and structured knowledge building. RAS interleaves targeted retrieval planning with incremental graph construction, enabling models to assemble and reason over evolving knowledge structures tailored to each query. On seven knowledge-intensive benchmarks, RAS consistently outperforms strong baselines, achieving up to 6.4% and 7.0% gains with open-source and proprietary LLMs, respectively. Our results demonstrate that dynamic, query-specific knowledge structuring offers a robust path to improving reasoning accuracy and robustness in language model generation. Our data and code can be found at https://github.com/pat-jj/RAS.

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="2502.10996")

Code

Syntology Ran 1 of 13 code samples harvested from 3 repositories linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 11 samples from 2 repositories, 0 ran; community: 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pat-jj/ras officialmentioned in paperpytorchApache-2.0 report
pat-jj/Retrieval-And-Structure officialmentioned 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

13 samples harvested; 1 ran; 0 honoured the contract we drafted; 12 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
12unverified

Licence: 2 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

convert_index_to_l2 pat-jj/Retrieval-And-Structure/archived/theme_dense_ret_gpu_v1.py official repository unverified Apache-2.0 (permissive) · b17548f37cf21541 · report
cpu_cuda pat-jj/Retrieval-And-Structure/baselines/start_knowtrace_retrieval_server_cpu.py official repository unverified Apache-2.0 (permissive) · 56a4c2457dfdb116 · report
find_ras_result_files pat-jj/ras/framework/evaluate_ras_results.py official repository unverified Apache-2.0 (permissive) · 6645463255861c20 · report
load_and_filter_indices pat-jj/Retrieval-And-Structure/archived/split_indices.py official repository unverified Apache-2.0 (permissive) · abe55d649017f1d8 · report
load_data pat-jj/ras/framework/run_ras_pre.py official repository unverified Apache-2.0 (permissive) · 4e5819f26351b1ef · report
load_knowledge pat-jj/Retrieval-And-Structure/archived/theme_dense_ret.py official repository unverified Apache-2.0 (permissive) · 9f3a09d9e617e3b3 · report
load_knowledge pat-jj/Retrieval-And-Structure/archived/theme_dense_ret_all.py official repository unverified Apache-2.0 (permissive) · 775f52b9a2fccf7b · report
load_knowledge pat-jj/Retrieval-And-Structure/archived/theme_dense_ret_gpu_v1.py official repository unverified Apache-2.0 (permissive) · 0fca4db50662c50f · report
prepare_split_mappings pat-jj/Retrieval-And-Structure/archived/split_efficient.py official repository unverified Apache-2.0 (permissive) · 742860f487a75103 · report
retrieve pat-jj/Retrieval-And-Structure/archived/theme_dense_ret.py official repository unverified Apache-2.0 (permissive) · 87ab1eb8f4c9f280 · report
save_faiss_index_safely pat-jj/Retrieval-And-Structure/archived/theme_dense_ret_gpu_v2.py official repository unverified Apache-2.0 (permissive) · dcab01df1508833b · report
bge_rerank_result haruhi-sudo/rpg/inference/long_form_demo.py community ran · our draft was wrong no licence file found · pointer only · 32b42053b96ab3ff · report
generate_text_iter haruhi-sudo/rpg/inference/long_form_demo.py community unverified no licence file found · pointer only · c65ec42fd5ea52f5 · report

Tasks

Knowledge GraphsLanguage ModelingLanguage ModellingRAGRetrievalRetrieval-augmented Generationgraph construction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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