SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02760 · 2024

Erasing Conceptual Knowledge from Language Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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; 3 failures of our instrument; 4 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/2410.02760.json · badge: /api/ran/2410.02760.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
rohitgandikota/erasing-llm canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
generate Ran
ran; our contract draft was wrong, not the code
rohitgandikota/erasing-llm/trainscripts/erase.py
pointer only (licence: NONE) · get_code("a13ff0028dc689e7")
How it ran

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

generate Ran
ran; our contract draft was wrong, not the code
rohitgandikota/erasing-llm/trainscripts/prepare_consistency_data.py
pointer only (licence: NONE) · get_code("868ded444472e56d")
How it ran

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

prepare_prompts Ran
ran; our contract draft was wrong, not the code
rohitgandikota/erasing-llm/trainscripts/erase.py
pointer only (licence: NONE) · get_code("822e559e4fe066e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rohitgandikota/erasing-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_accuracy Not yet run
unverified (harvested, no recorded run)
rohitgandikota/erasing-llm/utils/metrics.py
pointer only (licence: NONE) · get_code("c1aaeda27d027041")
How it ran

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

get_accuracy_binary Not yet run
unverified (harvested, no recorded run)
rohitgandikota/erasing-llm/utils/metrics.py
pointer only (licence: NONE) · get_code("97a23d1f1385fc72")
How it ran

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

get_edit_vector Not yet run
unverified (harvested, no recorded run)
rohitgandikota/erasing-llm/trainscripts/erase.py
pointer only (licence: NONE) · get_code("1b37a9d657d8b81c")
How it ran

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

get_wmdp_accuracy Not yet run
unverified (harvested, no recorded run)
rohitgandikota/erasing-llm/utils/metrics.py
pointer only (licence: NONE) · get_code("360cccb0e5753168")
How it ran

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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 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.

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

In this work, we introduce Erasure of Language Memory (ELM), a principled approach to concept-level unlearning that operates by matching distributions defined by the model's own introspective classification capabilities. Our key insight is that effective unlearning should leverage the model's ability to evaluate its own knowledge, using the language model itself as a classifier to identify and reduce the likelihood of generating content related to undesired concepts. ELM applies this framework to create targeted low-rank updates that reduce generation probabilities for concept-specific content while preserving the model's broader capabilities. We demonstrate ELM's efficacy on biosecurity, cybersecurity, and literary domain erasure tasks. Comparative evaluation reveals that ELM-modified models achieve near-random performance on assessments targeting erased concepts, while simultaneously preserving generation coherence, maintaining benchmark performance on unrelated tasks, and exhibiting strong robustness to adversarial attacks. Our code, data, and trained models are available at https://elm.baulab.info

For agents

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

get_harvested_code_for_paper("2410.02760")
get_code_for_paper("2410.02760")
have("2410.02760")

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

curl https://syntology.ai/api/ran/2410.02760.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.02760.svg)](https://syntology.ai/paper/2410.02760)

Connect an agent — have() is free.