SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.06483 · ICLR · 2025

Composable Interventions for Language Models

Tianlong Chen, Marinka Zitnik, Shiwei Liu, Huang, Arinbjörn Kolbeinsson, Shanghua Gao, Faisal Mahmood, Anurag Vaidya, Kyle O'brien, Tianjin Eleutherai, Jonathan Richard, Schwarz Thomson-Reuters, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

8 of 17 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 2 have no contract verdict; 6 failures of our instrument; 9 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/2407.06483.json · badge: /api/ran/2407.06483.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
hartvigsen-group/composable-interventions canonical (classifier label)
classifier basis: census
8 ran · 9 no recorded run
FunctionStatusWhere it lives
binary_log_probs Ran
ran; our contract draft was wrong, not the code
hartvigsen-group/composable-interventions/easyeditor/trainer/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from MemEIC/MemEIC, is pointer only (licence: NONE) · get_code("27659a9c234ffb11")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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.

generate_fingerprint Ran
ran; our contract draft was wrong, not the code
hartvigsen-group/composable-interventions/run_edit.py
pointer only (licence: NONE) · get_code("ae77bcc993ab559a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_wikitext2 Ran
ran on a synthesized input
hartvigsen-group/composable-interventions/sparsellm/lib/data.py
pointer only (licence: NONE); the stored copy get_code serves, from zyxxmu/dsnot, is pointer only (licence: NONE) · get_code("dee8be97b2cf4692")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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.

hierarchical_subsequence Ran
ran on a synthesized input
hartvigsen-group/composable-interventions/easyeditor/util/nethook.py
pointer only (licence: NONE) · get_code("920b394e7ad80c53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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.

kl_loc_loss Ran
ran; our contract draft was wrong, not the code
hartvigsen-group/composable-interventions/easyeditor/trainer/losses.py
pointer only (licence: NONE) · get_code("bcc592aa5c1e2bb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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.

masked_mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hartvigsen-group/composable-interventions/easyeditor/trainer/losses.py
pointer only (licence: NONE) · get_code("e078eeed20f03838")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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.

recursive_copy Ran
ran; our contract draft was wrong, not the code
hartvigsen-group/composable-interventions/easyeditor/util/nethook.py
pointer only (licence: NONE); the stored copy get_code serves, from TrustedLLM/UnKE, is pointer only (licence: NONE) · get_code("70f6ab8bde55420e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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.

subsequence Ran
ran; our contract draft was wrong, not the code
hartvigsen-group/composable-interventions/easyeditor/util/nethook.py
pointer only (licence: NONE) · get_code("440ff98c2b1ae1aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_args Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/main_quantize.py
pointer only (licence: NONE) · get_code("48bcc4bf8834c89a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_c4 Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/sparsellm/lib/data.py
pointer only (licence: NONE) · get_code("823f33725cd8f75d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_c4 Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/sparsellm/lib/datautils.py
pointer only (licence: NONE) · get_code("1ebe223f71f863bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_ga_data Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/ga_utils.py
pointer only (licence: NONE) · get_code("e9098552690ff1e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_loaders Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/sparsellm/lib/data.py
pointer only (licence: NONE) · get_code("d280312c1c709fbb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_model Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/easyeditor/trainer/models.py
pointer only (licence: NONE); the stored copy get_code serves, from llm-editing/HalluEditBench, is pointer only (licence: NONE) · get_code("d2e4c1979dd70b9a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_ptb Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/sparsellm/lib/datautils.py
pointer only (licence: NONE) · get_code("3a6ac4325dad94a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_tokenizer Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/easyeditor/trainer/models.py
pointer only (licence: NONE) · get_code("2defe42cf1a7f301")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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_wikitext2 Not yet run
unverified (harvested, no recorded run)
hartvigsen-group/composable-interventions/sparsellm/lib/datautils.py
pointer only (licence: NONE) · get_code("ce2dbbe16d039626")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hartvigsen-group/composable-interventions 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 8 the same month, 9 later) and 7 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
subsequence 49 other papers
25 dated earlier, 1 the same month, 22 later, 1 same year, order not determinable
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2009.05041 (2020-09)
Understanding the Role of Individual Units in a Deep Neural Network
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
and 46 more not named here
recursive_copy 48 other papers
24 dated earlier, 1 the same month, 22 later, 1 same year, order not determinable
2207.02774 (2022-07)
Local Relighting of Real Scenes
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
and 45 more not named here
hierarchical_subsequence 46 other papers
22 dated earlier, 1 the same month, 22 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
and 43 more not named here
binary_log_probs 28 other papers
14 dated earlier, 1 the same month, 12 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
and 25 more not named here
kl_loc_loss 16 other papers
8 dated earlier, 1 the same month, 7 later
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2401.04700 (2024-01)
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
2401.17623 (2024-01)
Neighboring Perturbations of Knowledge Editing on Large Language Models
and 13 more not named here
get_wikitext2 15 other papers
8 dated earlier, 5 later, 2 same year, order not determinable · 1 only as an assembly brick
2306.11695 (2023-06)
A Simple and Effective Pruning Approach for Large Language Models
2310.01382 (2023-10)
Compressing LLMs: The Truth is Rarely Pure and Never Simple
2310.05175 (2023-10)
Outlier Weighed Layerwise Sparsity (OWL ): A Missing Secret Sauce for Pruning LLMs to High Sparsity
and 12 more not named here
get_tokenizer 14 other papers
8 dated earlier, 1 the same month, 5 later
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2401.04700 (2024-01)
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
2401.17623 (2024-01)
Neighboring Perturbations of Knowledge Editing on Large Language Models
and 11 more not named here
masked_mean 10 other papers
3 dated earlier, 1 the same month, 6 later
2206.06520 (2022-06)
Memory-Based Model Editing at Scale
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2406.11194 (2024-06)
In-Context Editing: Learning Knowledge from Self-Induced Distributions
and 7 more not named here
get_model 8 other papers
5 dated earlier, 1 the same month, 2 later
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2401.04700 (2024-01)
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
2402.11905 (2024-02)
Learning to Edit: Aligning LLMs with Knowledge Editing
and 5 more not named here
get_ptb 1 other paper
1 dated earlier
2406.00800 (2024-06)
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization

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

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories-knowledge editing, model compression, and machine unlearning. Our results over 417 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions. 1

For agents

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

get_harvested_code_for_paper("2407.06483")
get_code_for_paper("2407.06483")
have("2407.06483")

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

curl https://syntology.ai/api/ran/2407.06483.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.06483.svg)](https://syntology.ai/paper/2407.06483)

Connect an agent — have() is free.