Ethan Perez, Roman Ring, Trevor Cai, Francis Song, John Aslanides, Saffron Huang, A. Glaese, Nat McAleese, G. Irving
1 of 1 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 0 have no contract verdict; 1 failure of our instrument; 0 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/2202.03286.json · badge: /api/ran/2202.03286.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 |
|---|---|---|
| shreyansh26/Red-Teaming-Language-Models-with-Language-Models | reimplementation (classifier label) classifier basis: classifier_2025 |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| swor_gumbel | Ran ran; our contract draft was wrong, not the code |
shreyansh26/Red-Teaming-Language-Models-with-Language-Models/generate_questions_few_shot.py pointer only (licence: NONE) · get_code("4d854d88e070847f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, shreyansh26/Red-Teaming-Language-Models-with-Language-Models 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. |
Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Language Models (LMs) often cannot be deployed because of their potential to harm users in ways that are hard to predict in advance. Prior work identifies harmful behaviors before deployment by using human annotators to handwrite test cases. However, human annotation is expensive, limiting the number and diversity of test cases. In this work, we automatically find cases where a target LM behaves in a harmful way, by generating test cases ("red teaming") using another LM. We evaluate the target LM's replies to generated test questions using a classifier trained to detect offensive content, uncovering tens of thousands of offensive replies in a 280B parameter LM chatbot. We explore several methods, from zero-shot generation to reinforcement learning, for generating test cases with varying levels of diversity and difficulty. Furthermore, we use prompt engineering to control LM-generated test cases to uncover a variety of other harms, automatically finding groups of people that the chatbot discusses in offensive ways, personal and hospital phone numbers generated as the chatbot's own contact info, leakage of private training data in generated text, and harms that occur over the course of a conversation. Overall, LM-based red teaming is a promising tool for finding and fixing diverse, undesirable LM behaviors before impacting users. classifiers.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.03286")
get_code_for_paper("2202.03286")
have("2202.03286")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2202.03286.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2202.03286)
Connect an agent — have() is free.