SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.00801 · NeurIPS · 2024

Self-Retrieval: End-to-End Information Retrieval with One Large Language Model

Haiyang Yu, Fei Huang, Jiawei Chen, Yongbin Li, Bowen Yu, Qiaoyu Tang, Zhuoqun Li, Yaojie Lu, Cheng Fu, Hongyu Lin, Ben He, Xianpei Han, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.00801.json · badge: /api/ran/2403.00801.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
icip-cas/selfretrieval canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
tangqiaoyu/selfretrieval marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_final_results_from_prefix Ran
ran; our contract draft was wrong, not the code
icip-cas/selfretrieval/evaluation/predict.py
pointer only (licence: NONE) · get_code("fab65e2bedd8dec0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, icip-cas/selfretrieval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

self_assessment Ran
ran, honoured the contract we drafted
icip-cas/selfretrieval/evaluation/predict.py
pointer only (licence: NONE) · get_code("d208bd8d5e5bdb52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, icip-cas/selfretrieval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Retriever Not yet run
unverified (harvested, no recorded run)
tangqiaoyu/selfretrieval/evaluation/predict.py
pointer only (licence: NONE) · get_code("0cfdc6cb7b4cd04e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tangqiaoyu/selfretrieval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

constrain_func Not yet run
unverified (harvested, no recorded run)
icip-cas/selfretrieval/evaluation/predict.py
pointer only (licence: NONE) · get_code("55a6e80874eda228")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, icip-cas/selfretrieval when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions between IR systems and LLMs remain limited, with LLMs merely serving as part of components within IR systems, and IR systems being constructed independently of LLMs. This separated architecture restricts knowledge sharing and deep collaboration between them. In this paper, we introduce Self-Retrieval, a novel end-to-end LLM-driven information retrieval architecture. Self-Retrieval unifies all essential IR functions within a single LLM, leveraging the inherent capabilities of LLMs throughout the IR process. Specifically, Self-Retrieval internalizes the retrieval corpus through self-supervised learning, transforms the retrieval process into sequential passage generation, and performs relevance assessment for reranking. Experimental results demonstrate that Self-Retrieval not only outperforms existing retrieval approaches by a significant margin, but also substantially enhances the performance of LLM-driven downstream applications like retrieval-augmented generation. 3

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.00801")
get_code_for_paper("2403.00801")
have("2403.00801")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.00801.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.00801.svg)](https://syntology.ai/paper/2403.00801)

Connect an agent — have() is free.