SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.09306 · NeurIPS · 2023

Propagating Knowledge Updates to LMs Through Distillation

Greg Durrett, Michael Zhang, Eunsol Choi, Shankar Padmanabhan, Yasumasa Onoe

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2306.09306.json · badge: /api/ran/2306.09306.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
shankarp8/knowledge_distillation canonical (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_specificity_ecbd Ran
ran; our contract draft was wrong, not the code
shankarp8/knowledge_distillation/src/edit_func.py
pointer only (licence: NONE) · get_code("d23db44d1a2e99aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shankarp8/knowledge_distillation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_specificity_entity_inferences Ran
ran; our contract draft was wrong, not the code
shankarp8/knowledge_distillation/src/edit_func.py
pointer only (licence: NONE) · get_code("90fa81c5637fcec8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shankarp8/knowledge_distillation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
shankarp8/knowledge_distillation/src/edit_func.py
pointer only (licence: NONE) · get_code("64ab493370e4f4c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shankarp8/knowledge_distillation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_log_probs Ran
ran; our contract draft was wrong, not the code
shankarp8/knowledge_distillation/src/edit_func.py
pointer only (licence: NONE) · get_code("c02311c2e53bf28a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shankarp8/knowledge_distillation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ft_distill_gpt Not yet run
unverified (harvested, no recorded run)
shankarp8/knowledge_distillation/src/edit_func.py
pointer only (licence: NONE) · get_code("1db31f7a27d2cecf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shankarp8/knowledge_distillation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

gpt_distill_after_entity_span Not yet run
unverified (harvested, no recorded run)
shankarp8/knowledge_distillation/src/edit_func.py
pointer only (licence: NONE) · get_code("36c41cba2ff4aa42")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shankarp8/knowledge_distillation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Modern language models have the capacity to store and use immense amounts of knowledge about real-world entities, but it remains unclear how to update such knowledge stored in model parameters. While prior methods for updating knowledge in LMs successfully inject atomic facts, updated LMs fail to make inferences based on injected facts. In this work, we demonstrate that a context distillation-based approach can both impart knowledge about entities and propagate that knowledge to enable broader inferences. Our approach consists of two stages: transfer set generation and distillation on the transfer set. We first generate a transfer set by prompting a language model to generate continuations from the entity definition. Then, we update the model parameters so that the distribution of the LM (the 'student') matches the distribution of the LM conditioned on the definition (the 'teacher') on the transfer set. Our experiments demonstrate that this approach is more effective at propagating knowledge updates than finetuning and other gradient-based knowledge-editing methods. Moreover, it does not compromise performance in other contexts, even when injecting the definitions of up to 150 entities at once. As large language models (LLMs) are used for a wider variety of applications, it is crucial to ensure that they contain up-to-date information about the world. One potential solution is retrieval augmentation, which prepends retrieved texts to the language model's context [20,29,35,34]. However, this raises inference costs and becomes impractical when updating large amounts of information. An alternative approach, and our goal in this work, is to internalize the new knowledge into the language model via parameter updates [36,44,8,26,22,12]. Recent work on injecting LLMs with information about emerging entities [32] demonstrates that updating parameters effectively enables models to acquire updated facts (Rishi Sunak is the prime minister of the UK), but struggles to teach models how to propagate this knowledge, or make inferences based on it (what might Rishi Sunak do tomorrow?). This contrasts with results from retrieval augmentation [20,35] and chain-of-thought prompting [40], which show that LLMs can make such inferences when information is placed in the prompt. This work aims to bridge the gap between the two approaches in knowledge injection. We use a form of knowledge distillation [13] called context distillation [1] that updates an LM to act like it is conditioned on a given context, even when that context is not shown. Our approach consists of two steps: transfer set generation and distillation on the generated transfer set. The transfer set consists of continuations of the entity definition sentence generated by prompting a language model. To distill on this transfer set, we minimize the Kullback-Leibler (KL) divergence between the model's predictions 37th Conference on Neural Information Processing Systems (NeurIPS 2023).

For agents

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

get_harvested_code_for_paper("2306.09306")
get_code_for_paper("2306.09306")
have("2306.09306")

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

curl https://syntology.ai/api/ran/2306.09306.json

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

[![Syntology run record](https://syntology.ai/api/ran/2306.09306.svg)](https://syntology.ai/paper/2306.09306)

Connect an agent — have() is free.