Papers › Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning

6 May 2024arXiv:2405.03279archive 2025-07-28

Qizhou Chen, Taolin Zhang, Xiaofeng He, Dongyang Li, Chengyu Wang, Longtao Huang, Hui Xue

Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging task that caters to the continuous editing requirements of LLMs. Prior works primarily focus on single or batch editing; nevertheless, these methods fall short in lifelong editing scenarios due to catastrophic knowledge forgetting and the degradation of model performance. Although retrieval-based methods alleviate these issues, they are impeded by slow and cumbersome processes of integrating the retrieved knowledge into the model. In this work, we introduce RECIPE, a RetriEval-augmented ContInuous Prompt lEarning method, to boost editing efficacy and inference efficiency in lifelong learning. RECIPE first converts knowledge statements into short and informative continuous prompts, prefixed to the LLM's input query embedding, to efficiently refine the response grounded on the knowledge. It further integrates the Knowledge Sentinel (KS) that acts as an intermediary to calculate a dynamic threshold, determining whether the retrieval repository contains relevant knowledge. Our retriever and prompt encoder are jointly trained to achieve editing properties, i.e., reliability, generality, and locality. In our experiments, RECIPE is assessed extensively across multiple LLMs and editing datasets, where it achieves superior editing performance. RECIPE also demonstrates its capability to maintain the overall performance of LLMs alongside showcasing fast editing and inference speed.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qizhou000/RECIPE officialpytorchSyntology: 11 samples, 7 ran (3 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested: 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
4ran
4unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qizhou000/RECIPE. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its 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.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at 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 cleared, but the stored copy of the same code that Syntology serves is not. 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

qizhou000/RECIPE official repository 11 samples, 7 ran (3 instrument-failed) · 4 unverified
KnowledgeRepModel editors/recipe/recipe.py ran MIT (permissive) · 7af30496f8e6ecb5 · report fixture: returned KnowledgeRepModel · level recorded 2026-09-22
ParallelDataset editors/recipe/recipe.py ran MIT (permissive) · 804969a3f054faa8 · report fixture: returned ParallelDataset · level recorded 2026-09-22
PromptTransformer editors/recipe/recipe.py ran MIT (permissive) · 65642b6f8132e7c7 · report fixture: returned PromptTransformer · level recorded 2026-09-22
RECIPEConfig editors/recipe/recipe.py ran MIT (permissive) · b84382c69b38db7f · report fixture: returned RECIPEConfig · level recorded 2026-09-22
find_module in 14 papers editors/recipe/recipe.py ran · our draft was wrong MIT (permissive) · 0b7bebf9d95d540c · report fixture: signature module:callable/0/?, module_path:str/0/str · returned Linear · level recorded 2026-09-22
hinge_label_loss editors/recipe/recipe.py ran · our draft was wrong MIT (permissive) · 532d15ae38761ef5 · report fixture: signature model:callable/0/?, input_ids:Tensor/2/int, label_ids:Tensor/2/int, masks:Tensor/2/float, average:bool/0/bool, eps:float/0/float, hinge_scale:float/0/float · returned Tensor · level recorded 2026-09-22
logit_KL_loss editors/recipe/recipe.py ran · our draft was wrong fingerprinted MIT (permissive) · 1897158165b40b18 · report fixture: signature logits1:Tensor/3/float, logits2:Tensor/3/float, masks:Tensor/2/float, average:bool/0/bool · returned Tensor · level recorded 2026-09-22
BaseEditor editors/recipe/recipe.py unverified MIT (permissive) · 11dd857ade8eded8 · report
EditorConfig editors/recipe/recipe.py unverified MIT (permissive) · 972549486d7dfecb · report
RECIPE editors/recipe/recipe.py unverified MIT (permissive) · 8c1cfd9a64ce7e2e · report
set_tokenizer_pad_id editors/recipe/recipe.py unverified MIT (permissive) · 062542a916d19f67 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for RECIPE (graph method: RECIPE). 11 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. RECIPE entry · level 0 · unverified · 8c1cfd9a64ce7e2e
  2. BaseEditor helper · level 0 · unverified · 11dd857ade8eded8
  3. KnowledgeRepModel model · level 1 · ran · 7af30496f8e6ecb5
  4. ParallelDataset helper · level 1 · ran · 804969a3f054faa8
  5. PromptTransformer model · level 1 · ran · 65642b6f8132e7c7
  6. RECIPEConfig helper · level 1 · ran · b84382c69b38db7f
  7. find_module helper · level 1 · ran · our draft was wrong · 0b7bebf9d95d540c
  8. hinge_label_loss loss · level 1 · ran · our draft was wrong · 532d15ae38761ef5
  9. logit_KL_loss loss · level 1 · ran · our draft was wrong · 1897158165b40b18
  10. set_tokenizer_pad_id helper · level 0 · unverified · 062542a916d19f67
  11. EditorConfig helper · level 0 · unverified · 972549486d7dfecb

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.03279") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Lifelong learningModel EditingPrompt LearningRetrievalknowledge editing

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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