SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.04320 · ACL · 2023

Unified Demonstration Retriever for In-Context Learning

Xipeng Qiu, Kai Lv, Wei Zhu, Yuan Ni, Hang Yan, Xiaoling Wang, Xiaonan Li, Tianya Lin, G. Xie

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 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/2305.04320.json · badge: /api/ran/2305.04320.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
KaiLv69/UDR community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
BiEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
KaiLv69/UDR/DPR/dpr/models/biencoder.py
pointer only (licence: NONE) · get_code("b3d28ee836daee7a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaiLv69/UDR 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.

_select_span_with_token Ran
ran, honoured the contract we drafted
KaiLv69/UDR/DPR/dpr/models/biencoder.py
pointer only (licence: NONE) · get_code("1e17fe064ad9b435")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaiLv69/UDR 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.

BiEncoderSample Not yet run
unverified (harvested, no recorded run)
KaiLv69/UDR/DPR/dpr/models/biencoder.py
pointer only (licence: NONE) · get_code("c39c9e2c36175c74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KaiLv69/UDR 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
BiEncoderSample
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2004.04906 (2020-04)
Dense Passage Retrieval for Open-Domain Question Answering
_select_span_with_token
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2004.04906 (2020-04)
Dense Passage Retrieval for Open-Domain Question Answering

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

In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. It has been shown highly dependent on the provided demonstrations and thus promotes the research of demonstration retrieval: given a test input, relevant examples are retrieved from the training set to serve as informative demonstrations for in-context learning. While previous works focus on training task-specific retrievers for several tasks separately, these methods are often hard to transfer and scale on various tasks, and separately trained retrievers incur a lot of parameter storage and deployment cost. In this paper, we propose Unified Demonstration Retriever (UDR), a single model to retrieve demonstrations for a wide range of tasks. To train UDR, we cast various tasks' training signals into a unified list-wise ranking formulation by language model's feedback. Then we propose a multi-task list-wise ranking training framework, with an iterative mining strategy to find high-quality candidates, which can help UDR fully incorporate various tasks' signals. Experiments on 30+ tasks across 13 task families and multiple data domains show that UDR significantly outperforms baselines. Further analyses show the effectiveness of each proposed component and UDR's strong ability in various scenarios including different LMs (1.3B ∼ 175B), unseen datasets, varying demonstration quantities, etc.

For agents

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

get_harvested_code_for_paper("2305.04320")
get_code_for_paper("2305.04320")
have("2305.04320")

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

curl https://syntology.ai/api/ran/2305.04320.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.04320.svg)](https://syntology.ai/paper/2305.04320)

Connect an agent — have() is free.