SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09488 · NAACL · 2024

Rectifying Demonstration Shortcut in In-Context Learning

Sanghwan Jang, Hwanjo Yu, Joonwon Jang, Wonbin Kweon, Minjin Jeon

arXiv · PDF · Open in the Atlas

Code that ran

3 of 9 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; 2 failures of our instrument; 6 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/2403.09488.json · badge: /api/ran/2403.09488.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
lainshower/in-context-calibration marked official in Papers with Code
Papers with Code archive
3 ran · 6 no recorded run
FunctionStatusWhere it lives
chunk_size_helper Ran
ran, honoured the contract we drafted
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("76931defc8580476")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

chunks Ran
ran; our contract draft was wrong, not the code
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("bdf1c41b44f672f1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

construct_prompt Ran
ran; our contract draft was wrong, not the code
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("e37bbdf75acd586c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

complete Not yet run
unverified (harvested, no recorded run)
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("49196c172c60c041")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

complete_gpt2 Not yet run
unverified (harvested, no recorded run)
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("50f02fdb39cbb530")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

complete_gpt3 Not yet run
unverified (harvested, no recorded run)
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("b5797bb0c80ce893")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

get_model_response Not yet run
unverified (harvested, no recorded run)
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("b18ccaa5f7df5e9f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

setup_gpt2 Not yet run
unverified (harvested, no recorded run)
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("cdfcb2d8e8a5acda")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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.

setup_gpt3 Not yet run
unverified (harvested, no recorded run)
lainshower/in-context-calibration/utils.py
pointer only (licence: NONE) · get_code("2224bc9059d64ea5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lainshower/in-context-calibration 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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
chunks
brick of this paper's assembly: helper
1 other paper
1 later
2606.22627 (2026-06)
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs

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

Large language models (LLMs) are able to solve various tasks with only a few demonstrations utilizing their in-context learning (ICL) abilities. However, LLMs often rely on their pre-trained semantic priors of demonstrations rather than on the input-label relationships to proceed with ICL prediction. In this work, we term this phenomenon as the 'Demonstration Shortcut'. While previous works have primarily focused on improving ICL prediction results for predefined tasks, we aim to rectify the Demonstration Shortcut, thereby enabling the LLM to effectively learn new input-label relationships from demonstrations. To achieve this, we introduce In-Context Calibration, a demonstration-aware calibration method. We evaluate the effectiveness of the proposed method in two settings: (1) the Original ICL Task using the standard label space and (2) the Task Learning setting, where the label space is replaced with semantically unrelated tokens. In both settings, In-Context Calibration demonstrates substantial improvements, with results generalized across three LLM families (OPT, GPT, and Llama2) under various configurations. 1 * Corresponding author 1 https://github.com/Lainshower/ In-Context-Calibration.git Classify the news articles into the categories of World, Sports, Business, and Technology.

For agents

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

get_harvested_code_for_paper("2403.09488")
get_code_for_paper("2403.09488")
have("2403.09488")

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

curl https://syntology.ai/api/ran/2403.09488.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.09488.svg)](https://syntology.ai/paper/2403.09488)

Connect an agent — have() is free.