SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.23746 · NeurIPS · 2024

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

Xinyi Yang, Derek Wong, Lidia Chao, Nlp, Runzhe Zhan, Shu Yang, Junchao Wu, Yulin Yuan

arXiv · PDF · Open in the Atlas

Code that ran

5 of 16 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, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 11 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/2410.23746.json · badge: /api/ran/2410.23746.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
nlp2ct/detectrl canonical (classifier label)
classifier basis: census
4 ran · 11 no recorded run
NLP2CT/DetectRL reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_bm25_retriver Ran
ran; our contract draft was wrong, not the code
nlp2ct/detectrl/Data_Generation/data_generation.py
pointer only (licence: NONE) · get_code("0178d9374b7ab0be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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_sampling_discrepancy_analytic Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nlp2ct/detectrl/Detectors/Fast_DetectGPT.py
pointer only (licence: NONE) · get_code("cd334919390112d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

lexical_diversity Ran
ran, honoured the contract we drafted
NLP2CT/DetectRL/Analysis/benchmark_statistics/statistics_lexical_diversity.py
pointer only (licence: NONE) · get_code("accb4f4eb000e081")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NLP2CT/DetectRL 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.

sample_multiple_of_four Ran
ran, honoured the contract we drafted
nlp2ct/detectrl/Data_Generation/data_mixing.py
pointer only (licence: NONE) · get_code("e4e96676b2972694")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

tokenize_and_mask Ran
ran; our contract draft was wrong, not the code
nlp2ct/detectrl/Detectors/DetectGPT.py
pointer only (licence: NONE) · get_code("6bef9b8781ddec1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

bt_translation Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Data_Generation/data_generation.py
pointer only (licence: NONE) · get_code("125ca1328bad554f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

chat_deepinfra Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Data_Generation/Chat_API.py
pointer only (licence: NONE) · get_code("3173c07643d9b286")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

chat_openai Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Data_Generation/Chat_API.py
pointer only (licence: NONE) · get_code("71794aa47e77d1cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

count_masks Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Detectors/DetectGPT.py
pointer only (licence: NONE) · get_code("23c3416429f69fee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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_ll Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Detectors/loss.py
pointer only (licence: NONE) · get_code("e2fc29bd5a992600")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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_lls Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Detectors/loss.py
pointer only (licence: NONE) · get_code("d0cd5a24eb8ebb54")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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_sentences_in_paragraph Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Data_Generation/data_mixing.py
pointer only (licence: NONE) · get_code("e86e359f633b93cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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_text_crit Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Detectors/Fast_DetectGPT.py
pointer only (licence: NONE) · get_code("c3a387dd367bcfa3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

read_data Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Data_Generation/DIPPER.py
pointer only (licence: NONE) · get_code("0af108cefcec3d33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

replace_masks Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Detectors/DetectGPT.py
pointer only (licence: NONE) · get_code("cd67487f05408843")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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.

spilt_paragraph Not yet run
unverified (harvested, no recorded run)
nlp2ct/detectrl/Data_Generation/DIPPER.py
pointer only (licence: NONE) · get_code("150e39aff29a1dc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp2ct/detectrl 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 15 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
count_masks 11 other papers
9 dated earlier, 2 later
2023.emnlp-main.616 (2023 (year only))
MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
2303.14822 (2023-03)
MGTBench: Benchmarking Machine-Generated Text Detection
2305.18462 (2023-05)
Membership Inference Attacks against Language Models via Neighbourhood Comparison
and 8 more not named here

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

Detecting text generated by large language models (LLMs) is of great recent interest. With zero-shot methods like DetectGPT, detection capabilities have reached impressive levels. However, the reliability of existing detectors in real-world applications remains underexplored. In this study, we present a new benchmark, DetectRL, highlighting that even state-of-the-art (SOTA) detection techniques still underperformed in this task. We collected human-written datasets from domains where LLMs are particularly prone to misuse. Using popular LLMs, we generated data that better aligns with real-world applications. Unlike previous studies, we employed heuristic rules to create adversarial LLM-generated text, simulating various prompts usages, human revisions like word substitutions, and writing noises like spelling mistakes. Our development of DetectRL reveals the strengths and limitations of current SOTA detectors. More importantly, we analyzed the potential impact of writing styles, model types, attack methods, the text lengths, and real-world human writing factors on different types of detectors. We believe Detec-tRL could serve as an effective benchmark for assessing detectors in real-world scenarios, evolving with advanced attack methods, thus providing more stressful evaluation to drive the development of more efficient detectors. 2 * Corresponding author 2 Data and code are publicly available at: https://github.com/NLP2CT/DetectRL 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks.

For agents

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

get_harvested_code_for_paper("2410.23746")
get_code_for_paper("2410.23746")
have("2410.23746")

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

curl https://syntology.ai/api/ran/2410.23746.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.23746.svg)](https://syntology.ai/paper/2410.23746)

Connect an agent — have() is free.