Papers › Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning

Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning

29 Feb 2024arXiv:2402.18865archive 2025-07-28

Weijieying Ren, Xinlong Li, Lei Wang, Tianxiang Zhao, Wei Qin

Existing research has shown that large language models (LLMs) exhibit remarkable performance in language understanding and generation. However, when LLMs are continuously fine-tuned on complex and diverse domain-specific downstream tasks, the inference performance on historical tasks decreases dramatically, which is known as a catastrophic forgetting problem. A trade-off needs to be kept between learning plasticity and memory stability. Plenty of existing works have explored strategies like memory replay, regularization and parameter isolation, but little is known about the geometric connection of various adjacent minima in the continual LLMs fine-tuning scenarios. In this work, we investigate the geometric connections of different minima through the lens of mode connectivity, which means different minima can be connected by a low-loss valley. Through extensive experiments, we uncover the mode connectivity phenomenon in the LLMs continual learning scenario and find that it can strike a balance between plasticity and stability. Building upon these findings, we propose a simple yet effective method called Interpolation-based LoRA (I-LoRA), which constructs a dual-memory experience replay framework based on LoRA parameter interpolations. Extensive experiments and analysis on eight domain-specific CL benchmarks demonstrate that I-LoRA consistently show significant improvement over the previous state-of-the-art approaches with up to 11% performance gains, providing a strong baseline and insights for future research on the large language model continual learning problem. Our code is available at https://github.com/which47/LLMCL.

PaperPDFCodeCode Syntology ran

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: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

which47/llmcl officialmentioned in paperpytorchSyntology: 11 samples, 9 ran (2 instrument-failed) · 2 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: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · our draft was wrong
4ran
2unverified

Licence: 11 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 which47/llmcl. “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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

which47/llmcl official repository 11 samples, 9 ran (2 instrument-failed) · 2 unverified
concat_inputs method/ER.py ran no licence file found · pointer only · 18b8186589457eb4 · report fixture: signature input_ids:Tensor/2/int, attention_mask:Tensor/2/int, labels:Tensor/2/int, buffer_input_ids:Tensor/2/int, buffer_attention_mask:Tensor/2/int, buffer_labels:Tensor/2/int · returned tuple · level recorded 2026-09-24
get_joint_datasets get_dataset.py ran · our draft was wrong no licence file found · pointer only · dbea6b5c8c82bfb1 · report fixture: signature datasets:dict/0/? · returned dict · level recorded 2026-09-24
get_res in 7 papers evaluation.py ran · honoured contract no licence file found · pointer only · f6fd640bd5fb5f16 · report fixture: signature result:dict/0/?, name:str/0/str · returned float · level recorded 2026-09-24
l2_normalize in 40 papers
census: 15 implementations from 13 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
method/L2P.py ran fingerprinted no licence file found · pointer only · d16edbaed144f08d · report fixture: signature x:Tensor/2/float, dim:int/0/int, epsilon:float/0/float · returned Tensor · level recorded 2026-09-24
list_strings utils/arg_configs.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9a37fcbe00419582 · report fixture: signature string:str/0/str · returned list · level recorded 2026-09-24
reservoir in 8 papers method/ILORA.py ran · honoured contract fingerprinted no licence file found · pointer only · 7e522e4817696b98 · report fixture: signature num_seen_examples:int/0/int, buffer_size:int/0/int · returned int · level recorded 2026-09-22
reservoir in 8 papers method/ER.py ran · honoured contract fingerprinted no licence file found · pointer only · 04102179b159097d · report fixture: signature num_seen_examples:int/0/int, buffer_size:int/0/int · returned int · level recorded 2026-09-24
ring method/ILORA.py ran fingerprinted no licence file found · pointer only · 3ea09d9b15eac6ea · report fixture: signature num_seen_examples:int/0/int, buffer_portion_size:int/0/int, task:int/0/int · returned int · level recorded 2026-09-24
run_generation inference.py ran no licence file found · pointer only · 68c73a68bb1fa2f3 · report fixture: signature model:callable/0/?, tokenizer:callable/0/?, name:str/0/str, test_dataloader:list/1/dict, generation_config:GenerationConfig/0/? · returned list · level recorded 2026-09-24
get_datasets in 49 papers get_dataset.py unverified no licence file found · pointer only · d90e6d4a6e725608 · report
prepare_model_for_inference inference.py unverified no licence file found · pointer only · 4277a360496e0802 · report

Tasks

Continual LearningLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Experience Replay

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