SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.07937 · 2026

HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy

Weihua Luo, Liang Zhang, Longyue Wang, Hui Li, Hao Fu, Jinsong Su, Yujie Lin, Guoqi Ma, Hongyao Tu

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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; 2 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2604.07937.json · badge: /api/ran/2604.07937.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
XMUDeepLIT/HCRE canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
FunctionStatusWhere it lives
create_score_evaluation_response Ran
ran on a synthesized input
XMUDeepLIT/HCRE/train/src/llamafactory/api/chat.py
pointer only (licence: NONE); the stored copy get_code serves, from 125jx/SeqLLM, is pointer only (licence: NONE) · get_code("dbea5358be6b5ad0")
How it ran

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

edit_distance Ran
ran, honoured the contract we drafted
XMUDeepLIT/HCRE/inference/utils.py
pointer only (licence: NONE) · get_code("79c199943c57a674")
How it ran

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

extract_code Ran
ran; our contract draft was wrong, not the code
XMUDeepLIT/HCRE/auto-tree/utils.py
pointer only (licence: NONE) · get_code("495dba1ca2e724dc")
How it ran

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

format_tree Ran
ran; our contract draft was wrong, not the code
XMUDeepLIT/HCRE/auto-tree/main-meaningful_levels_v2.py
pointer only (licence: NONE) · get_code("56747310fcb05729")
How it ran

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

get_missing_and_invalid Ran
ran; our contract draft was wrong, not the code
XMUDeepLIT/HCRE/auto-tree/main-meaningful_levels_v2.py
pointer only (licence: NONE) · get_code("66a9fa337d0dc4a0")
How it ran

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

get_pos_path_num Ran
ran, honoured the contract we drafted
XMUDeepLIT/HCRE/auto-tree/main-meaningful_levels_v2.py
pointer only (licence: NONE) · get_code("759e23f601b2c5ad")
How it ran

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

int2roman Ran
ran; our contract draft was wrong, not the code
XMUDeepLIT/HCRE/inference/utils.py
pointer only (licence: NONE) · get_code("5d068fb3f5d9c87b")
How it ran

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

mean Ran
ran, violated the contract we drafted
XMUDeepLIT/HCRE/inference/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from schrammlb2/USHER_Implementation, is pointer only (licence: NONE) · get_code("e8b6cf1e9387fc9a")
How it ran

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

read_from_jsonl Ran
ran; our contract draft was wrong, not the code
XMUDeepLIT/HCRE/auto-tree/utils.py
pointer only (licence: NONE) · get_code("b9e30c120203c7f6")
How it ran

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

compute_metrics Not yet run
unverified (harvested, no recorded run)
XMUDeepLIT/HCRE/inference/eval_predictions.py
pointer only (licence: NONE) · get_code("f00a11019513fa38")
How it ran

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

hamming_similarity Not yet run
unverified (harvested, no recorded run)
XMUDeepLIT/HCRE/auto-tree/utils.py
pointer only (licence: NONE) · get_code("be53327170b067a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, XMUDeepLIT/HCRE 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 later) and 9 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
create_score_evaluation_response 23 other papers
18 dated earlier, 1 the same month, 4 later
2405.04760 (2024-05)
Large Language Models for Cyber Security: A Systematic Literature Review
2406.04496 (2024-06)
Time Sensitive Knowledge Editing through Efficient Finetuning
2411.06839 (2024-11)
LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models
and 20 more not named here
mean 3 other papers
3 dated earlier
2109.04096 (2021-09)
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
2207.01115 (2022-07)
USHER: Unbiased Sampling for Hindsight Experience Replay
2504.18397 (2025-04)
Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

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

to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of "Small Language Model (SLM) + Classifier". However, the limited language understanding ability of SLMs hinders further improvement of their performance. In this paper, we conduct a preliminary study to explore the performance of Large Language Models (LLMs) in crossdocument RE. Despite their extensive parameters, our findings indicate that LLMs do not consistently surpass existing SLMs. Further analysis suggests that the underperformance is largely attributed to the challenges posed by the numerous predefined relations. To overcome this issue, we propose an LLM-based Hierarchical Classification model for crossdocument RE (HCRE), which consists of two core components: 1) an LLM for relation prediction and 2) a hierarchical relation tree derived from the predefined relation set. This tree enables the LLM to perform hierarchical classification, where the target relation is inferred level by level. Since the number of child nodes is much smaller than the size of the entire predefined relation set, the hierarchical relation tree significantly reduces the number of relation options that LLM needs to consider during inference. However, hierarchical classification introduces the risk of error propagation across levels. To mitigate this, we propose a prediction-then-verification inference strategy that improves prediction reliability through multi-view verification at each level. Extensive experiments show that HCRE outperforms existing baselines, validating its effectiveness. We release our code at https: //github.com/XMUDeepLIT/HCRE.

For agents

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

get_harvested_code_for_paper("2604.07937")
get_code_for_paper("2604.07937")
have("2604.07937")

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

curl https://syntology.ai/api/ran/2604.07937.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.07937.svg)](https://syntology.ai/paper/2604.07937)

Connect an agent — have() is free.