SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.09651 · ACL · 2023

Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation

Yi Zhu, Mu Li, Xingjian Shi, Chun Yuan, Zihan Zhong, Yuxin Ren

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.09651.json · badge: /api/ran/2305.09651.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
twinkle0331/lgtm marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
LGTMTeacher Ran
ran on a synthesized input · constructed an object; no result was computed
twinkle0331/lgtm/utils_glue.py
code served (permissive licence) · get_code("d602427ea8902b34")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, LGTMTeacher: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim.lr_scheduler import StepLR

torch.manual_seed(0)

# Create a minimal teacher model
class TeacherModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=3):
        super().__init__()
        self.linear1 = nn.Linear(input_dim, 8)
        self.linear2 = nn.Linear(8, output_dim)
    
    def forward(self, input_ids=None, attention_mask=None, token_type_ids=None, **kwargs):
        x = torch.relu(self.linear1(input_ids))
        logits = self.linear2(x)
        loss = torch.tensor(0.5, requires_grad=True)
        return type('Output', (), {'loss': loss, 'logits': logits})()

# Create a minimal student model
class StudentModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=3):
        super().__init__()
        self.linear1 = nn.Linear(input_dim, 8)
        self.linear2 = nn.Linear(8, output_dim)
    
    def forward(self, input_ids=None, attention_mask=None, token_type_ids=None, **kwargs):
        x = torch.relu(self.linear1(input_ids))
        logits = self.linear2(x)
        loss = torch.tensor(0.3, requires_grad=True)
        return type('Output', (), {'loss': loss, 'logits': logits})()

# Instantiate models
teacher_model = TeacherModel(input_dim=4, output_dim=3)
student_model = StudentModel(input_dim=4, output_dim=3)

# Create optimizers
optimizer_t = optim.Adam(teacher_model.parameters(), lr=0.001, betas=(0.9, 0.999), eps=1e-8, weight_decay=0.0)

# Create scheduler
scheduler_t = StepLR(optimizer_t, step_size=1, gamma=0.1)

# Parameters
alpha_kd = 0.5
alpha_kd_t = 0.5
temperature = 3.0

ARGS = {
    'teacher_model': teacher_model,
    'student_model': student_model,
    'alpha_kd': alpha_kd,
    'alpha_kd_t': alpha_kd_t,
    'optimizer_t': optimizer_t,
    'scheduler_t': scheduler_t,
    'temperature': temperature,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LGTMTeacher — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a LGTMTeacher output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
cal_loss Ran
ran; our contract draft was wrong, not the code
twinkle0331/lgtm/utils_glue.py
code served (permissive licence) · get_code("940dcf82641060b8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for s_logits and t_logits
# Both should have shape (batch_size, num_classes)
# Using batch=2, num_classes=4 for small size
batch_size = 2
num_classes = 4

s_logits = torch.randn(batch_size, num_classes)
t_logits = torch.randn(batch_size, num_classes)

# Temperature is a scalar float value
temperature = 4.0

ARGS = {
    "s_logits": s_logits,
    "t_logits": t_logits,
    "temperature": temperature
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
cal_loss
brick of this paper's assembly: loss
1 other paper
1 later
2411.06448 (2024-11)
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

It has been commonly observed that a teacher model with superior performance does not necessarily result in a stronger student, highlighting a discrepancy between current teacher training practices and effective knowledge transfer. In order to enhance the guidance of the teacher training process, we introduce the concept of distillation influence to determine the impact of distillation from each training sample on the student's generalization ability. In this paper, we propose Learning Good Teacher Matters (LGTM), an efficient training technique for incorporating distillation influence into the teacher's learning process. By prioritizing samples that are likely to enhance the student's generalization ability, our LGTM outperforms 10 common knowledge distillation baselines on 6 text classification tasks in the GLUE benchmark. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.09651")
get_code_for_paper("2305.09651")
have("2305.09651")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.09651.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.09651.svg)](https://syntology.ai/paper/2305.09651)

Connect an agent — have() is free.