SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.06555 · 2023

LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 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/2311.06555.json · badge: /api/ran/2311.06555.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
hzzhou01/hd-loa-prompting canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
ans_extraction Ran
ran; our contract draft was wrong, not the code
hzzhou01/hd-loa-prompting/HD_LoA/DocEE/main_DocEE.py
pointer only (licence: NONE) · get_code("932df8cf8a209475")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hzzhou01/hd-loa-prompting 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.

ans_extraction Ran
ran; our contract draft was wrong, not the code
hzzhou01/hd-loa-prompting/HD_LoA/RAMS/main_RAMS.py
pointer only (licence: NONE) · get_code("3d73ee1369520558")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hzzhou01/hd-loa-prompting 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.

ans_extraction_gpt4 Ran
ran; our contract draft was wrong, not the code
hzzhou01/hd-loa-prompting/HD_LoA/DocEE/main_DocEE.py
pointer only (licence: NONE) · get_code("1c76fac1fd53438a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hzzhou01/hd-loa-prompting 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.

evaluate_prompt Ran
ran on a synthesized input
hzzhou01/hd-loa-prompting/HD_LoA/RAMS/main_RAMS.py
pointer only (licence: NONE) · get_code("1543a653267f84a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hzzhou01/hd-loa-prompting 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.

gen_gpt_output Ran
ran; our contract draft was wrong, not the code
hzzhou01/hd-loa-prompting/HD_LoA/DocEE/main_DocEE.py
pointer only (licence: NONE) · get_code("3fa776ff46467ded")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hzzhou01/hd-loa-prompting 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.

gen_gpt_output Not yet run
unverified (harvested, no recorded run)
hzzhou01/hd-loa-prompting/HD_LoA/RAMS/main_RAMS.py
pointer only (licence: NONE) · get_code("38f63e86116069ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hzzhou01/hd-loa-prompting 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting to address the challenge of example selection and to develop a prompting strategy tailored for EAE. Specifically, we hypothesize and validate that LLMs learn task-specific heuristics from demonstrations via ICL. Building upon this hypothesis, we introduce an explicit heuristic-driven demonstration construction approach, which transforms the haphazard example selection process into a methodical method that emphasizes task heuristics. Additionally, inspired by the analogical reasoning of human, we propose the link-of-analogy prompting, which enables LLMs to process new situations by drawing analogies to known situations, enhancing their performance on unseen classes beyond limited ICL examples. Experiments show that our method outperforms existing prompting methods and few-shot supervised learning methods on document-level EAE datasets. Additionally, the HD-LoA prompting shows effectiveness in diverse tasks like sentiment analysis and natural language inference, demonstrating its broad adaptability.

For agents

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

get_harvested_code_for_paper("2311.06555")
get_code_for_paper("2311.06555")
have("2311.06555")

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

curl https://syntology.ai/api/ran/2311.06555.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.06555.svg)](https://syntology.ai/paper/2311.06555)

Connect an agent — have() is free.