Papers › Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions

Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions

28 Feb 2024arXiv:2402.18025archive 2025-07-28

Kexun Zhang, Yee Man Choi, Zhenqiao Song, Taiqi He, William Yang Wang, Lei LI

How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a grammar book, and morphologically analyzed input text. We implement LINGOLLM on top of two models, GPT-4 and Mixtral, and evaluate their performance on 5 tasks across 8 endangered or low-resource languages. Our results show that LINGOLLM elevates translation capability from GPT-4's 0 to 10.5 BLEU for 10 language directions. Our findings demonstrate the tremendous value of linguistic knowledge in the age of LLMs for endangered languages. Our data, code, and model generations can be found at https://github.com/LLiLab/llm4endangeredlang.

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="2402.18025")

Code

Syntology Ran 8 of 13 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 13 samples from 2 repositories, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

leililab/lingollm officialmentioned in paper report
llilab/llm4endangeredlang officialmentioned in paper 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; 8 ran; 0 honoured the contract we drafted; 5 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 · our draft was wrong
7ran
5unverified

Licence: 13 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

check_dirs leililab/lingollm/gen.py official repository ran · our draft was wrong no licence file found · pointer only · 30da774c0f8a0676 · report
convert_to_underscore llilab/llm4endangeredlang/fst_src/helpers.py official repository ran fingerprinted no licence file found · pointer only · 29ec22f0d27d611e · report
extract_enclosed_text llilab/llm4endangeredlang/lingollm/prompts.py official repository ran fingerprinted no licence file found · pointer only · 8157b0711c048d1a · report
join_words llilab/llm4endangeredlang/fst_src/helpers.py official repository ran fingerprinted no licence file found · pointer only · 574259fb71503801 · report
match_score llilab/llm4endangeredlang/fst_src/ilg_helpers.py official repository ran fingerprinted no licence file found · pointer only · fa9257629938eebf · report
prompt_direct_translate llilab/llm4endangeredlang/lingollm/prompts.py official repository ran fingerprinted no licence file found · pointer only · b58c65537e96ba58 · report
prompt_system llilab/llm4endangeredlang/lingollm/prompts.py official repository ran fingerprinted no licence file found · pointer only · c22687ed59d1d97f · report
unique llilab/llm4endangeredlang/fst_src/helpers.py official repository ran fingerprinted no licence file found · pointer only · 05d917a26d659ced · report
copy_prompt_translate llilab/llm4endangeredlang/lingollm/pipelines.py official repository unverified no licence file found · pointer only · 0e208bbcdc29e798 · report
direct_translate llilab/llm4endangeredlang/lingollm/pipelines.py official repository unverified no licence file found · pointer only · 96fa86c8caacc090 · report
filter_matching_glosses llilab/llm4endangeredlang/fst_src/ilg_helpers.py official repository unverified no licence file found · pointer only · a5bac802f1de6944 · report
fst_to_story_gloss llilab/llm4endangeredlang/fst_src/ilg_helpers.py official repository unverified no licence file found · pointer only · 072c586b35001aee · report
get_llm_wrapper llilab/llm4endangeredlang/lingollm/llms.py official repository unverified no licence file found · pointer only · ece1a00a1f1f6b9b · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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