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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2310.06987.json · badge: /api/ran/2310.06987.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.
| Repository | Role | Ran |
|---|---|---|
| princeton-sysml/jailbreak_llm | canonical (classifier label) classifier basis: classifier_2025 |
5 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| clean_answer | Ran ran; our contract draft was wrong, not the code |
princeton-sysml/jailbreak_llm/evaluate.py pointer only (licence: NONE) · get_code("8c5418f18b5585e9") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-sysml/jailbreak_llm 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_eval_scores | Ran ran, honoured the contract we drafted |
princeton-sysml/jailbreak_llm/evaluate.py pointer only (licence: NONE) · get_code("1a0b16a21a2dc39f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-sysml/jailbreak_llm 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_sentence_embedding | Ran ran, honoured the contract we drafted |
princeton-sysml/jailbreak_llm/attack.py pointer only (licence: NONE) · get_code("027df82b1c46ec8c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-sysml/jailbreak_llm 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. |
| not_matched | Ran ran; our contract draft was wrong, not the code |
princeton-sysml/jailbreak_llm/evaluate.py pointer only (licence: NONE) · get_code("33fe41321aa1cf43") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-sysml/jailbreak_llm 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. |
| prepend_sys_prompt | Ran ran; our contract draft was wrong, not the code |
princeton-sysml/jailbreak_llm/attack.py pointer only (licence: NONE) · get_code("4b3e0b154c70a7d9") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-sysml/jailbreak_llm 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. |
| main | Not yet run unverified (harvested, no recorded run) |
princeton-sysml/jailbreak_llm/attack.py pointer only (licence: NONE) · get_code("1791f231faab1a9d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, princeton-sysml/jailbreak_llm 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. |
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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 3 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| not_matched | 2 other papers 2 later |
2401.17256 (2024-01) Weak-to-Strong Jailbreaking on Large Language Models Content warning: This paper contains examples of harmful language |
2404.13968 (2024-04) Protecting Your LLMs with Information Bottleneck |
| clean_answer | 1 other paper 1 later |
2501.01872 (2025-01) Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions ! WARNING: This paper contains model outputs that may be considered offensive in nature |
|
| get_eval_scores | 1 other paper 1 later |
2501.01872 (2025-01) Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions ! WARNING: This paper contains model outputs that may be considered offensive in nature |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The rapid progress in open-source large language models (LLMs) is significantly advancing AI development. Extensive efforts have been made before model release to align their behavior with human values, with the primary goal of ensuring their helpfulness and harmlessness. However, even carefully aligned models can be manipulated maliciously, leading to unintended behaviors, known as "jailbreaks". These jailbreaks are typically triggered by specific text inputs, often referred to as adversarial prompts. In this work, we propose the generation exploitation attack, an extremely simple approach that disrupts model alignment by only manipulating variations of decoding methods. By exploiting different generation strategies, including varying decoding hyper-parameters and sampling methods, we increase the misalignment rate from 0% to more than 95% across 11 language models including LLaMA2, Vicuna, Falcon, and MPT families, outperforming state-of-the-art attacks with $30\times$ lower computational cost. Finally, we propose an effective alignment method that explores diverse generation strategies, which can reasonably reduce the misalignment rate under our attack. Altogether, our study underscores a major failure in current safety evaluation and alignment procedures for open-source LLMs, strongly advocating for more comprehensive red teaming and better alignment before releasing such models. Our code is available at https://github.com/Princeton-SysML/Jailbreak_LLM.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.06987")
get_code_for_paper("2310.06987")
have("2310.06987")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2310.06987.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2310.06987)
Connect an agent — have() is free.