Papers › LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin

LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin

15 Dec 2023arXiv:2312.09979archive 2025-07-28

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Jun Zhao, Wei Shen, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Xiaoran Fan, ShiLiang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks. Increasing instruction data substantially is a direct solution to align the model with a broader range of downstream tasks or notably improve its performance on a specific task. However, we find that large-scale increases in instruction data can damage the world knowledge previously stored in LLMs. To address this challenge, we propose LoRAMoE, a novelty framework that introduces several low-rank adapters (LoRA) and integrates them by using a router network, like a plugin version of Mixture of Experts (MoE). It freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge-edge forgetting. Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2312.09979")

Code

Syntology Ran 7 of 14 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ablustrund/loramoe officialmentioned in papermentioned on GitHubjax 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

14 samples harvested; 7 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
6ran
7unverified

Licence: 14 of the 14 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 ablustrund/loramoe. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

convert_pytorch_state_dict_to_flax ablustrund/loramoe/transformers/modeling_flax_pytorch_utils.py official repository ran no licence file found · pointer only · 5168a172bbb363a5 · report
get_imports ablustrund/loramoe/transformers/dynamic_module_utils.py official repository ran no licence file found · pointer only · ccaa0edba373622c · report
infer_metric_tags_from_eval_results ablustrund/loramoe/transformers/modelcard.py official repository ran no licence file found · pointer only · dd8f7751ef859581 · report
parse_keras_history ablustrund/loramoe/transformers/modelcard.py official repository ran no licence file found · pointer only · a4491b45d19b7a39 · report
prepare_model_for_kbit_training ablustrund/loramoe/run_loramoe.py official repository ran · our draft was wrong no licence file found · pointer only · 591cff6b55ba6bfb · report
quick_gelu ablustrund/loramoe/transformers/modeling_flax_utils.py official repository ran fingerprinted no licence file found · pointer only · a66d2b78670c85e1 · report
rename_key_and_reshape_tensor ablustrund/loramoe/transformers/modeling_flax_pytorch_utils.py official repository ran no licence file found · pointer only · 61779b0406a59cfc · report
build_instruction_dataset ablustrund/loramoe/build_dataset.py official repository unverified no licence file found · pointer only · 2776dfe4cf53097d · report
dtype_byte_size ablustrund/loramoe/transformers/modeling_flax_utils.py official repository unverified no licence file found · pointer only · 9d98806acb3144b7 · report
flax_shard_checkpoint ablustrund/loramoe/transformers/modeling_flax_utils.py official repository unverified no licence file found · pointer only · e3ce70ca9258800e · report
forward ablustrund/loramoe/flash_attn_patch.py official repository unverified no licence file found · pointer only · 602b6b6c04496cfd · report
get_relative_import_files ablustrund/loramoe/transformers/dynamic_module_utils.py official repository unverified no licence file found · pointer only · 00cc853a73f3aeb6 · report
get_relative_imports ablustrund/loramoe/transformers/dynamic_module_utils.py official repository unverified no licence file found · pointer only · 450aeffe7f80f917 · report
is_hf_dataset ablustrund/loramoe/transformers/modelcard.py official repository unverified no licence file found · pointer only · ec7b1528a936234d · report

Tasks

Language ModellingMixture-of-ExpertsMulti-Task LearningWorld Knowledge

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNFocus

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