Home › Code › kl_loc_loss

kl_loc_loss

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

kl_loc_loss appears in the code Syntology harvested for 28 papers, as 3 distinct code bodies found in 28 places (a place is one code body under one paper). Of the 28 papers, 28 with a sample that ran: 18 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument. 1 of the code bodies carries a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named kl_loc_loss do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 3 distinct code bodies named kl_loc_loss: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
0ran; the contract check could not run
2ran
0unverified
1fingerprinted

Licence is a property of each copy, so it is counted per place: 17 of the 28 places are pointer only (Syntology does not serve that copy's text); at 5 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Papers

28 papers shown of 28, newest first; 28 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing added by Syntology 2026-07 (from id) lab-klc/ScopeEdit/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models added by Syntology 2026-05 (from id) Wangzzzzzzzz/OTE-SE-Alignment/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong no licence file found · pointer only
Multiplicative Orthogonal Sequential Editing for Language Models added by Syntology 2026-01 (from id) famoustourist/MOSE/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge 27 Feb 2025 MMKE-Bench-ICLR/MMKE-Bench/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
The Mirage of Model Editing: Revisiting Evaluation in the Wild 16 Feb 2025 wanliyoung/revisit-editing-evaluation/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran Apache-2.0 (permissive)
arXiv:2502.03748 2025-02 (from id) xpq-tech/BLUE/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
Should We Really Edit Language Models? On the Evaluation of Edited Language Models 24 Oct 2024 zjunlp/EasyEdit/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
Can Knowledge Editing Really Correct Hallucinations? 21 Oct 2024 llm-editing/HalluEditBench/code/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
CollabEdit: Towards Non-destructive Collaborative Knowledge Editing 12 Oct 2024 LINs-lab/CollabEdit/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
Neuron-Level Sequential Editing for Large Language Models 5 Oct 2024 jianghoucheng/nse/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong no licence file found · pointer only
Can Editing LLMs Inject Harm? 29 Jul 2024 llm-editing/editing-attack/code/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
Composable Interventions for Language Models 9 Jul 2024 hartvigsen-group/composable-interventions/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces 17 Jun 2024 yihuaihong/conceptvectors/memit/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong CC-BY-4.0 · pointer only
In-Context Editing: Learning Knowledge from Self-Induced Distributions 17 Jun 2024 bigai-ai/ICE/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
Perturbation-Restrained Sequential Model Editing 27 May 2024 mjy1111/PRUNE/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
TAXI: Evaluating Categorical Knowledge Editing for Language Models 23 Apr 2024 derekpowell/taxi/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models 21 Mar 2024 orange-opensource/wikifactdiff/evaluate/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark 12 Mar 2024 VLKEB/VLKEB/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing 11 Mar 2024 scalable-model-editing/rebuilding-rome/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
Learning to Edit: Aligning LLMs with Knowledge Editing 19 Feb 2024 yjiangcm/lte/EasyEdit/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran Apache-2.0 (permissive)
Neighboring Perturbations of Knowledge Editing on Large Language Models 31 Jan 2024 mjy1111/PEAK/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
Model Editing at Scale leads to Gradual and Catastrophic Forgetting 15 Jan 2024 scalable-model-editing/gradual-catastrophic-forgetting/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong no licence file found · pointer only
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue 9 Jan 2024 jasonforjoy/model-editing-hurt/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
Assessing Knowledge Editing in Language Models via Relation Perspective 15 Nov 2023 weiyifan1023/knowledge-edit-based-on-relation-perspective/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong no licence file found · pointer only
Untying the Reversal Curse via Bidirectional Language Model Editing 16 Oct 2023 mjy1111/bake/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran no licence file found · pointer only
Mass-Editing Memory in a Transformer 13 Oct 2022 kmeng01/memit/baselines/mend/losses.py 8b02eb3a3733d653 ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
CVF open access id Zeng_Visual-Oriented_Fine-Grained_Knowledge_Editing_for_MultiModal_Large_Language_Models_ICCV_2025_paper zeng-zhen/FGVEdit/easyeditor/trainer/losses.py bcc592aa5c1e2bb3 ran MIT (permissive)
ACL Anthology id 2024.acl-long.732 wchrepo/mulfe/evaluation/baselines/mend/losses.py b5ffa288849b3969 ran fingerprinted Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections