SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.14670 · 2024

Exploring Design Choices for Building Language-Specific LLMs

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 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/2406.14670.json · badge: /api/ran/2406.14670.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
atutej/token-language-adaptation canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
compress Ran
ran; our contract draft was wrong, not the code
atutej/token-language-adaptation/FastChat/fastchat/model/compression.py
pointer only (licence: NONE); the stored copy get_code serves, from Git-King-Zhan/LoReC, is pointer only (licence: NONE) · get_code("80dde39da1ba3708")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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_stream_codet5p Ran
ran; our contract draft was wrong, not the code
atutej/token-language-adaptation/FastChat/fastchat/model/model_codet5p.py
pointer only (licence: NONE) · get_code("9921c5a2fe409afc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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_compressed_list Ran
ran; our contract draft was wrong, not the code
atutej/token-language-adaptation/FastChat/fastchat/model/compression.py
pointer only (licence: NONE); the stored copy get_code serves, from Git-King-Zhan/LoReC, is pointer only (licence: NONE) · get_code("c5824da57107fe8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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.

process_response Ran
ran; our contract draft was wrong, not the code
atutej/token-language-adaptation/FastChat/fastchat/model/model_chatglm.py
pointer only (licence: NONE) · get_code("dc21db7cf25bfe72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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.

raise_warning_for_incompatible_cpu_offloading_configuration Ran
ran, violated the contract we drafted
atutej/token-language-adaptation/FastChat/fastchat/model/model_adapter.py
pointer only (licence: NONE) · get_code("0bf414a2b44babe6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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_conv_template Not yet run
unverified (harvested, no recorded run)
atutej/token-language-adaptation/FastChat/fastchat/conversation.py
pointer only (licence: NONE) · get_code("506ee6d4bab01412")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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.

load_compress_model Not yet run
unverified (harvested, no recorded run)
atutej/token-language-adaptation/FastChat/fastchat/model/compression.py
pointer only (licence: NONE) · get_code("648d40deadeb4493")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atutej/token-language-adaptation 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 5 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
get_conv_template 69 other papers
28 dated earlier, 8 the same month, 28 later, 4 same year, order not determinable, 1 undated
1911.03705 (2019-11)
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2204.07705 (2022-04)
SUPER-NATURALINSTRUCTIONS: Generalization via Declarative Instructions on 1600+ NLP Tasks
and 66 more not named here
compress 17 other papers
12 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2303.06865 (2023-03)
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
2304.10453 (2023-04)
Phoenix: Democratizing ChatGPT across Languages
and 14 more not named here
raise_warning_for_incompatible_cpu_offloading_configuration 15 other papers
11 dated earlier, 4 later
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2310.13023 (2023-10)
GraphGPT: Graph Instruction Tuning for Large Language Models
2312.00401 (2023-12)
VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things
and 12 more not named here
get_compressed_list 13 other papers
8 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2310.13023 (2023-10)
GraphGPT: Graph Instruction Tuning for Large Language Models
2310.17631 (2023-10)
JudgeLM: Fine-tuned Large Language Models are Scalable Judges
and 10 more not named here
process_response 9 other papers
7 dated earlier, 1 later, 1 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2305.12524 (2023-05)
TheoremQA: A Theorem-driven Question Answering Dataset ♠
2310.17631 (2023-10)
JudgeLM: Fine-tuned Large Language Models are Scalable Judges
and 6 more not named here
generate_stream_codet5p 1 other paper
1 dated earlier
2402.01830 (2024-02)
PiCO: Peer Review in LLMs based on the Consistency Optimization

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

Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We conduct systematic experiments on how design choices (base model selection, vocabulary extension, and continued pretraining) impact the adapted LLM, both in terms of efficiency (how many tokens are needed to encode the same amount of information) and end task performance. We find that (1) the initial performance of LLM does not always correlate with the final performance after the adaptation. Adapting an English-centric models can yield better results than adapting multilingual models despite their worse initial performance on low-resource languages. (2) Efficiency can easily improved with simple vocabulary extension and continued pretraining in most LLMs we study, and (3) The optimal adaptation method (choice of the base model, new vocabulary size, training data, initialization strategy) is highly language-dependent, and the simplest embedding initialization works well across various experimental settings. Together, our work lays foundations on efficiently building language-specific LLMs by adapting existing LLMs.

For agents

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

get_harvested_code_for_paper("2406.14670")
get_code_for_paper("2406.14670")
have("2406.14670")

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

curl https://syntology.ai/api/ran/2406.14670.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.14670.svg)](https://syntology.ai/paper/2406.14670)

Connect an agent — have() is free.