# Cross-Lingual Steering for Figurative Language Generation

arXiv: https://arxiv.org/abs/2605.30443 · HTML: https://mlsanity.com/paper/2605.30443/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 54 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia](https://mlsanity.com/paper/1907.05791/) (2019)
- [COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval](https://mlsanity.com/paper/1805.08661/) (2018)
- [FLUTE: Figurative Language Understanding through Textual Explanations](https://mlsanity.com/paper/2205.12404/) (2022)
- [Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment](https://mlsanity.com/paper/2305.05940/) (2023)
- [Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models](https://mlsanity.com/paper/2504.04264/) (2025)
- [Probing the Emergence of Cross-lingual Alignment during LLM Training](https://mlsanity.com/paper/2406.13229/) (2024)
- [Understanding Cross-Lingual Alignment -- A Survey](https://mlsanity.com/paper/2404.06228/) (2024)
- [The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities](https://mlsanity.com/paper/2405.20089/) (2024)
- [Can Pre-trained Language Models Interpret Similes as Smart as Human?](https://mlsanity.com/paper/2203.08452/) (2022)
- [CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark](https://mlsanity.com/paper/2601.08331/) (2026)
- [COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics](https://mlsanity.com/paper/2603.06495/) (2026)
- [Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency](https://mlsanity.com/paper/2603.17102/) (2026)
- [BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset](https://mlsanity.com/paper/2205.14462/) (2022)
- [When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms](https://mlsanity.com/paper/2602.12921/) (2026)

## Built on by (most cited first, 1 of 1)

- [The Linear Representation Hypothesis Needs a Group Action](https://mlsanity.com/paper/2609.27158/) (2026)

## Abstract (arXiv)

Cross-lingual activation steering has been studied mainly for language-agnostic properties such as factual knowledge and reasoning. Its transferability remains unclear for figurative language, whose expressions are often tied to a particular language. In this work, we study cross-lingual steering of figurative language: whether steering vectors learned in one language can affect generation in another. We first show that within a single language, steering effectively increases the ratio of the intended figure of speech, especially for metaphor and idiom. Then under the cross-lingual setting, across 408 comparisons spanning four multilingual models, six languages, and four figures of speech, steering increases the figurative ratio from the unsteered 12.1% to 20.4%. To understand the mechanism, we decompose each language's own steering vector into the mean of steering vectors from other languages and a residual, and show that this mean direction matches or outperforms the language's own vector while the residual steers worse. This suggests that, despite the highly language-dependent nature of figurative expressions, a partially shared direction exists in the representation space that enables figurative knowledge to transfer across languages.