SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.16920 · 2024

Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 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/2407.16920.json · badge: /api/ran/2407.16920.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
ybseo-academy/TAALM canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
anneal_function Ran
ran, honoured the contract we drafted
ybseo-academy/TAALM/utils/RecAdam.py
pointer only (licence: NONE) · get_code("b8301a2a061e30a2")
How it ran

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

giveme_label_mask Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/evaluation_run.py
pointer only (licence: NONE) · get_code("9745751dcea1a41f")
How it ran

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

giveme_label_mask0 Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/ta_eval.py
pointer only (licence: NONE) · get_code("aa580f8ceb463858")
How it ran

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

giveme_label_mask_list Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/evaluation_run.py
pointer only (licence: NONE) · get_code("6f28ab856d890d85")
How it ran

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

giveme_label_mask_list Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/ta_eval.py
pointer only (licence: NONE) · get_code("0be42af713b24083")
How it ran

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

make_conv Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/ta_toolbox.py
pointer only (licence: NONE) · get_code("2594581b57a6f409")
How it ran

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

make_real_id Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/TAALM_train_run.py
pointer only (licence: NONE) · get_code("c52d48f5fb3ab33d")
How it ran

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

make_task Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/evaluation_run.py
pointer only (licence: NONE) · get_code("26e2ec638208bc5c")
How it ran

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

make_task Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/ta_eval.py
pointer only (licence: NONE) · get_code("f8a3fcc48b115cac")
How it ran

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

preprocess Ran
ran; our contract draft was wrong, not the code
ybseo-academy/TAALM/TAALM_train_run.py
pointer only (licence: NONE) · get_code("1e1cba6114cc9188")
How it ran

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

adamw Not yet run
unverified (harvested, no recorded run)
ybseo-academy/TAALM/utils/tool_TAALM/taalm_adamw.py
pointer only (licence: NONE) · get_code("57f800133f0342bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybseo-academy/TAALM 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)
ybseo-academy/TAALM/utils/kadapter/Llama2_Model_Kadapter.py
pointer only (licence: NONE) · get_code("cb4e99dd4b50f69d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybseo-academy/TAALM 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 0 later) and 9 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
10 dated earlier, 1 the same month
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
anneal_function 3 other papers
3 dated earlier · 1 only as an assembly brick
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2306.10790 (2023-06)
Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference
2311.08106 (2023-11)
Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models

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

Previous studies on continual knowledge learning (CKL) in large language models (LLMs) have predominantly focused on approaches such as regularization, architectural modifications, and rehearsal techniques to mitigate catastrophic forgetting. However, these methods naively inherit the inefficiencies of standard training procedures, indiscriminately applying uniform weight across all tokens, which can lead to unnecessary parameter updates and increased forgetting. To address these shortcomings, we propose a novel CKL approach termed Train-Attention-Augmented Language Model (TAALM), which enhances learning efficiency by dynamically predicting and applying weights to tokens based on their usefulness. This method employs a meta-learning framework that optimizes token importance predictions, facilitating targeted knowledge updates and minimizing forgetting. Also, we observe that existing benchmarks do not clearly exhibit the trade-off between learning and retaining, therefore we propose a new benchmark, \textsc{LAMA-ckl}, to address this issue. Through experiments conducted on both newly introduced and established CKL benchmarks, TAALM proves the state-of-the-art performance upon the baselines, and also shows synergistic compatibility when integrated with previous CKL approaches.

For agents

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

get_harvested_code_for_paper("2407.16920")
get_code_for_paper("2407.16920")
have("2407.16920")

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

curl https://syntology.ai/api/ran/2407.16920.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.16920.svg)](https://syntology.ai/paper/2407.16920)

Connect an agent — have() is free.