SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.09573 · EMNLP · 2023

Self-Detoxifying Language Models via Toxification Reversal

Jian Wang, Wenjie Li, Yi Cheng, Jiashuo Wang, Chak Leong

arXiv · PDF · Open in the Atlas

Code that ran

None of the 2 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (2 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/2310.09573.json · badge: /api/ran/2310.09573.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
cooperleong00/toxificationreversal canonical (classifier label)
classifier basis: census
0 ran · 2 no recorded run
FunctionStatusWhere it lives
load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
cooperleong00/toxificationreversal/models/gpt2/modeling_gpt2.py
pointer only (licence: NONE) · get_code("bc9fb74e483fb901")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cooperleong00/toxificationreversal 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.

load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
cooperleong00/toxificationreversal/models/gpt2/modeling_gpt2_innerdetox.py
pointer only (licence: NONE) · get_code("c87b238769f13efb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cooperleong00/toxificationreversal 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 0 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
load_tf_weights_in_gpt2 11 other papers
5 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
2206.11871 (2022-06)
Offline RL for Natural Language Generation with Implicit Language Q Learning
2211.09817 (2022-11)
On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
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

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and decoding-based. However, the former is often resource-intensive, while the latter relies on additional components and potentially compromises the generation fluency. In this paper, we propose a more lightweight approach that enables the PLM itself to achieve "selfdetoxification". Our method is built upon the observation that prepending a negative steering prompt can effectively induce PLMs to generate toxic content. At the same time, we are inspired by the recent research in the interpretability field, which formulates the evolving contextualized representations within the PLM as an information stream facilitated by the attention layers. Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers. Experimental results show that our approach, without any fine-tuning or extra components, can achieve comparable performance with state-of-the-art methods. 1 1 Code is available at https://github.com/ cooperleong00/ToxificationReversal *Equal contribution Toxic Non-Toxic Context Embeddings Toxification Process Generation Space MHSA MHSA MHSA MHSA MHSA MHSA Toxification Direction Toxification Reversal Direction

For agents

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

get_harvested_code_for_paper("2310.09573")
get_code_for_paper("2310.09573")
have("2310.09573")

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

curl https://syntology.ai/api/ran/2310.09573.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.09573.svg)](https://syntology.ai/paper/2310.09573)

Connect an agent — have() is free.