ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languages

• URL: http://arxiv.org/abs/2608.03505v2
• Date: Wed, 05 Aug 2026 01:59:09 GMT
• Title: ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languages
• Abstract summary: We present ConlangBench, the first large-scale benchmark for evaluating and training large language models.<n>We collect over 21M conlang-English parallel sentence pairs (including 430K pairs across the 20 non-Esperanto conlangs) and 321K vocabulary entries.<n>Training on ConlangBench also shows that models can learn all eight conlangs for which sufficient parallel corpora are available.
• Score: 21.243559466259004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Constructed languages (conlangs) are intentionally created human languages with a rich tradition of linguistic creativity. Despite their potential for studying language learning in large language models (LLMs), existing conlangs remain largely underexplored in LLM research. We present ConlangBench, the first large-scale benchmark for evaluating and training LLMs on 21 existing conlangs. We collect over 21M conlang-English parallel sentence pairs (including 430K pairs across the 20 non-Esperanto conlangs) and 321K vocabulary entries. In bidirectional translation experiments, we find that models perform better on a posteriori conlangs, whose vocabularies are derived from natural languages, reflecting the design characteristics of conlangs. Training on ConlangBench also shows that models can learn all eight conlangs for which sufficient parallel corpora are available, while their learning curves vary depending on how the conlangs were created. Our findings suggest that conlangs provide a unique testbed for investigating how LLMs acquire low-resource languages.

Related papers

• In-context Language Learning for Endangered Languages in Speech Recognition [15.294500162002345]
  We investigate whether large language models (LLMs) can learn unseen, low-resource languages through in-context learning (ICL)<n>We show ICL enables LLMs to achieve ASR performance that is comparable to or even surpasses dedicated language models trained specifically for these languages.
  arXiv  Detail & Related papers  (2025-05-26T18:38:59Z)
• One ruler to measure them all: Benchmarking multilingual long-context language models [31.669282956425658]
  We present ONERULER, a multilingual benchmark designed to evaluate long-context language models across 26 languages.<n>English is not the top-performing language on long-context tasks (ranked 6th out of 26), with Polish emerging as the top language.<n>In cross-lingual scenarios where instructions and context appear in different languages, performance can fluctuate by up to 20% depending on the instruction language.
  arXiv  Detail & Related papers  (2025-03-03T19:12:48Z)
• Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning [9.75748930802634]
  We study the power of in-context-learning to improve machine learning performance.<n>We consider an extremely simple domain: next token prediction on simple language tasks.<n>We find that LLMs uniformly underperform n-gram models on this task.
  arXiv  Detail & Related papers  (2025-01-06T07:57:51Z)
• The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model [59.357993924917]
  We study the evolution of multilingual capabilities in large language models (LLMs) during the pre-training process.<n>We propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities.<n>We propose a novel method to construct an optimized pre-training corpus for multilingual code LLMs.
  arXiv  Detail & Related papers  (2024-12-10T08:28:57Z)
• ZhoBLiMP: a Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese [18.90198316015052]
  We first introduce ZhoBLiMP, the most comprehensive benchmark of linguistic minimal pairs for Chinese. We then train 20 LMs of different sizes (14M to 1.4B) on Chinese corpora and evaluate them along with 14 off-the-shelf LLMs on ZhoBLiMP. The overall results indicate that Chinese grammar can be mostly learned by models with around 500M parameters, trained on 1B tokens with one epoch, showing limited benefits for further scaling.
  arXiv  Detail & Related papers  (2024-11-09T07:16:08Z)
• Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models [52.00446751692225]
  We present a novel and simple yet effective method called textbfDictionary textbfInsertion textbfPrompting (textbfDIP) When providing a non-English prompt, DIP looks up a word dictionary and inserts words' English counterparts into the prompt for LLMs. It then enables better translation into English and better English model thinking steps which leads to obviously better results.
  arXiv  Detail & Related papers  (2024-11-02T05:10:50Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• SambaLingo: Teaching Large Language Models New Languages [16.709876506515837]
  We present a comprehensive investigation into the adaptation of LLMs to new languages. Our study covers the key components in this process, including vocabulary extension and direct preference optimization. We scale these experiments across 9 languages and 2 parameter scales.
  arXiv  Detail & Related papers  (2024-04-08T19:48:36Z)
• Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions [49.97641297850361]
  LINGOLLM is a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. 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.
  arXiv  Detail & Related papers  (2024-02-28T03:44:01Z)
• Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models [2.7013338932521416]
  We advocate for the revival of vocabulary tests as a valuable tool for assessing Large Language Models (LLMs) performance. We evaluate seven LLMs using two vocabulary test formats across two languages and uncover surprising gaps in their lexical knowledge.
  arXiv  Detail & Related papers  (2023-10-23T08:45:12Z)
• The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants [80.4837840962273]
  We present Belebele, a dataset spanning 122 language variants. This dataset enables the evaluation of text models in high-, medium-, and low-resource languages.
  arXiv  Detail & Related papers  (2023-08-31T17:43:08Z)
• Chain-of-Dictionary Prompting Elicits Translation in Large Language Models [100.47154959254937]
  Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) We present a novel method, CoD, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities.
  arXiv  Detail & Related papers  (2023-05-11T05:19:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.