SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.15518 · 2024

Steering Without Side Effects: Improving Post-Deployment Control of Language Models

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 1 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/2406.15518.json · badge: /api/ran/2406.15518.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
asacooperstickland/kl-then-steer canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
filter_categorized_data Ran
ran, violated the contract we drafted
asacooperstickland/kl-then-steer/scripts/evaluate_results.py
pointer only (licence: NONE) · get_code("dfe731af737bb542")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, asacooperstickland/kl-then-steer 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.

remove_repeated_letters Ran
ran; our contract draft was wrong, not the code
asacooperstickland/kl-then-steer/scripts/evaluate_results.py
pointer only (licence: NONE) · get_code("6540510703c709c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, asacooperstickland/kl-then-steer 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.

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 2 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 2 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.

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 models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model queries are unproblematic and frequent retraining results in unstable user experience, methods for mitigation of worst-case behavior should be targeted. One such method is classifying inputs as potentially problematic, then selectively applying steering vectors on these problematic inputs, i.e. adding particular vectors to model hidden states. However, steering vectors can also negatively affect model performance, which will be an issue on cases where the classifier was incorrect. We present KL-then-steer (KTS), a technique that decreases the side effects of steering while retaining its benefits, by first training a model to minimize Kullback-Leibler (KL) divergence between a steered and unsteered model on benign inputs, then steering the model that has undergone this training. Our best method prevents 44% of jailbreak attacks compared to the original Llama-2-chat-7B model while maintaining helpfulness (as measured by MT-Bench) on benign requests almost on par with the original LM. To demonstrate the generality and transferability of our method beyond jailbreaks, we show that our KTS model can be steered to reduce bias towards user-suggested answers on TruthfulQA. Code is available: https://github.com/AsaCooperStickland/kl-then-steer.

For agents

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

get_harvested_code_for_paper("2406.15518")
get_code_for_paper("2406.15518")
have("2406.15518")

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

curl https://syntology.ai/api/ran/2406.15518.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.15518.svg)](https://syntology.ai/paper/2406.15518)

Connect an agent — have() is free.