Challenge: Existing tools for cross-lingual idiom-to-idiom equivalence evaluation are limited . figurative meanings are non-compositional and culturally grounded, making literal mappings unreliable.
Approach: They propose a gloss-pivoted benchmark where each idiom is anchored by an English gloss from Wiktionary.
Outcome: The proposed benchmark is based on a dictionary-anchored English idiom . a bias to literal translation is a dominant failure mode across diverse LLMs, the study shows .

Similar Papers

Understanding Cross-Lingual Alignment—A Survey (2024.findings-acl)

Copied to clipboard

Challenge: Cross-lingual alignment is the meaningful similarity of representations across languages in multilingual language models.
Approach: They propose a taxonomy of methods to improve cross-lingual alignment . they argue that an effective trade-off between language-neutral and language-specific information is key .
Outcome: The proposed methods can be applied to encoder models and encoder-decoder-only models . they show that language-neutral and language-specific information is key .
How to Align Multiple Signed Language Corpora for Better Sign-to-Sign Translations? (2025.naacl-long)

Copied to clipboard

Challenge: despite the growing need for advanced signing technologies, signed language resources remain scarce.
Approach: They propose a linguistically informed alignment algorithm that matches instances between signed languages . they compare similarities and differences across three signed languages to develop a model .
Outcome: The proposed algorithm performs well on automatic metrics for sign-to-sign translation and generation.
TokAlign: Efficient Vocabulary Adaptation via Token Alignment (2025.acl-long)

Copied to clipboard

Challenge: Tokenization is a foundational step for Large Language Models (LLMs) but low compression rate of vanilla tokenizers decelerates training and inference process.
Approach: They propose a method to replace the vocabulary of Large Language Models (LLMs) by learning a one-to-one mapping matrix for token IDs.
Outcome: The proposed method significantly improves multilingual text compression rates and vocabulary initialization for Large Language Models.
Hierarchical Mapping for Crosslingual Word Embedding Alignment (2020.tacl-1)

Copied to clipboard

Challenge: Existing strategies that map word embeddings into a crosslingual space are biased towards the choice of the pivot language.
Approach: They propose to map any two languages into a different middle space by learning mappings across languages in a hierarchical way.
Outcome: The proposed strategy significantly improves vocabulary induction scores in all existing benchmarks and in a new non-English–centered benchmark.
Creative and Context-Aware Translation of East Asian Idioms with GPT-4 (2024.findings-emnlp)

Copied to clipboard

Challenge: figurative language is a challenge for human translators, who often choose a context-aware translation . a set of commonly used idioms condenses its figurativ meaning into a few characters .
Approach: They evaluate whether GPT-4 can generate high-quality translations using Pareto-optimal prompting strategies that outperform translation engines from Google and DeepL.
Outcome: The proposed translations outperform translation engines from Google and DeepL at low cost.
CHENGYU-BENCH: Benchmarking Large Language Models for Chinese Idiom Understanding and Use (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks focus on narrow tasks such as multiple-choice cloze tests, isolated translation, or simple paraphrasing.
Approach: They propose a benchmark to measure Chinese idioms' cultural and contextual nuances . they evaluate 2,937 human-verified examples covering 1,765 common idiomes .
Outcome: The proposed benchmarks achieve 95% accuracy on Evaluative Connotation, but only 85% on Appropriateness and 40% top-1 accuracy in Open Cloze.
PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models exhibit reasonable multilingual abilities, despite predominantly English-centric pretraining.
Approach: They propose a framework that establishes multilingual alignment prior to language model pretraining and preserves this alignment using a code-switching strategy during pretraining.
Outcome: Experiments in a synthetic English to English-Clone setting show that PreAlign outperforms standard multilingual joint training in language modeling, zero-shot cross-lingual transfer, and cross-linguistic knowledge application.
Deep Generative Model for Joint Alignment and Word Representation (N18-1)

Copied to clipboard

Challenge: EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments.
Approach: They exploit translation as a distributional context and embed words as posterior probability densities, rather than point estimates, which allows them to compare words in context using a measure of overlap between distributions.
Outcome: The proposed model performs on a range of lexical semantics tasks and achieves competitive results on benchmarks including natural language inference, paraphrasing, and text similarity.
AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach: They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome: The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.
Exploring the Relationship between Alignment and Cross-lingual Transfer in Multilingual Transformers (2023.findings-acl)

Copied to clipboard

Challenge: despite lack of explicit cross-lingual training data, multilingual models can achieve cross-linguistic transfer.
Approach: They find alignment is significantly correlated with cross-lingual transfer . they advocate for further research on realignment methods for smaller models .
Outcome: The proposed method outperforms XLM-R Large in POS-tagging between English and Arabic by +15.8 accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations