Papers › Lifting the Curse of Capacity Gap in Distilling Language Models

Lifting the Curse of Capacity Gap in Distilling Language Models

20 May 2023arXiv:2305.12129archive 2025-07-28

Chen Zhang, Yang Yang, Jiahao Liu, Jingang Wang, Yunsen Xian, Benyou Wang, Dawei Song

Pretrained language models (LMs) have shown compelling performance on various downstream tasks, but unfortunately they require a tremendous amount of inference compute. Knowledge distillation finds a path to compress LMs to small ones with a teacher-student paradigm. However, when the capacity gap between the teacher and the student is large, a curse of capacity gap appears, invoking a deficiency in distilling LMs. While a few studies have been carried out to fill the gap, the curse is not yet well tackled. In this paper, we aim at lifting the curse of capacity gap via enlarging the capacity of the student without notably increasing the inference compute. Largely motivated by sparse activation regime of mixture of experts (MoE), we propose a mixture of minimal experts (MiniMoE), which imposes extra parameters to the student but introduces almost no additional inference compute. Experimental results on GLUE and CoNLL demonstrate the curse of capacity gap is lifted by the magic of MiniMoE to a large extent. MiniMoE also achieves the state-of-the-art performance at small FLOPs compared with a range of competitive baselines. With a compression rate as much as ∼50×, MiniMoE preserves ∼95\% GLUE score of the teacher.

PaperPDFCodeCode Syntology ran

In Syntology 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="2305.12129")

Code

Syntology Ran 5 of 13 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

genezc/minimoe officialmentioned in papermentioned on GitHubpytorch 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

13 samples harvested; 5 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
4ran
8unverified

Licence: 0 of the 13 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 genezc/minimoe. “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.

GateLinear genezc/minimoe/modules/modeling_moebert_gate.py official repository ran Apache-2.0 (permissive) · 6abd1347d0c44be3 · report
MoEBertEmbeddings genezc/minimoe/modules/modeling_moebert_gate.py official repository ran · metamorphic tier: invariant Apache-2.0 (permissive) · d059c2309fca697b · report
MoEBertIntermediate genezc/minimoe/modules/modeling_moebert_gate.py official repository ran fingerprinted Apache-2.0 (permissive) · 16f3cea91fa35e41 · report
MoEBertPooler genezc/minimoe/modules/modeling_moebert_gate.py official repository ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 2af6f69a908eee12 · report
one_hot genezc/minimoe/modules/modeling_moebert_gate.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 882d0552fedc5aa1 · report
MoEBertAttention genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · 0906fd483dd042ca · report
MoEBertEncoder genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · 215b29e96dbea836 · report
MoEBertLayer genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · ea3533cf6785ab2e · report
MoEBertModel genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · 29c6962b86d5b64c · report
MoEBertOutput genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · fbfad05bb8c37ef0 · report
MoEBertSelfAttention genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · a401370bc11c23ef · report
MoEBertSelfOutput genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · 09da8fe5de680832 · report
MoELinear genezc/minimoe/modules/modeling_moebert_gate.py official repository unverified Apache-2.0 (permissive) · abc80e95eaef3d78 · report

Tasks

Knowledge DistillationMixture-of-Experts

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge Distillation

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