# CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark

arXiv: https://arxiv.org/abs/2601.08331 · HTML: https://mlsanity.com/paper/2601.08331/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [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)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://mlsanity.com/paper/2309.09400/) (2023)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [MIB: A Mechanistic Interpretability Benchmark](https://mlsanity.com/paper/2504.13151/) (2025)
- [Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models](https://mlsanity.com/paper/2407.12824/) (2024)
- [From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP](https://mlsanity.com/paper/2406.12618/) (2024)
- [Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation](https://mlsanity.com/paper/2507.22608/) (2025)
- [Causal Language Control in Multilingual Transformers via Sparse Feature Steering](https://mlsanity.com/paper/2507.13410/) (2025)

## Built on by (most cited first, 12 of 12)

- [From Weights to Activations: Is Steering the Next Frontier of Adaptation?](https://mlsanity.com/paper/2604.14090/) (2026)
- [ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance](https://mlsanity.com/paper/2604.12378/) (2026)
- [Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection](https://mlsanity.com/paper/2605.23036/) (2026)
- [FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering](https://mlsanity.com/paper/2603.18329/) (2026)
- [LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering](https://mlsanity.com/paper/2604.03532/) (2026)
- [Cross-Lingual Steering for Figurative Language Generation](https://mlsanity.com/paper/2605.30443/) (2026)
- [The Latin Substrate: How Language Models Represent and Mediate Script Choice](https://mlsanity.com/paper/2605.31363/) (2026)
- [Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation](https://mlsanity.com/paper/2606.18389/) (2026)
- [Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs](https://mlsanity.com/paper/2609.01356/) (2026)
- [Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control](https://mlsanity.com/paper/2609.16967/) (2026)
- [MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation](https://mlsanity.com/paper/2609.38718/) (2026)
- [Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility](https://mlsanity.com/paper/2610.20139/) (2026)

## Abstract (arXiv)

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged as a more efficient and interpretable technique for adapting models to a target language. Yet, no dedicated benchmarks or evaluation protocols exist to quantify the effectiveness of steering techniques. We introduce CLaS-Bench, a lightweight parallel-question benchmark for evaluating language-forcing behavior in LLMs across 32 languages, enabling systematic evaluation of multilingual steering methods. We evaluate a broad array of steering techniques, including residual-stream DiffMean interventions, probe-derived directions, language-specific neurons, PCA/LDA vectors, Sparse Autoencoders, and prompting baselines. Steering performance is measured along two axes: language control and semantic relevance, combined into a single harmonic-mean steering score. We find that across languages simple residual-based DiffMean method consistently outperforms all other methods. Moreover, a layer-wise analysis reveals that language-specific structure emerges predominantly in later layers and steering directions cluster based on language family. CLaS-Bench is the first standardized benchmark for multilingual steering, enabling both rigorous scientific analysis of language representations and practical evaluation of steering as a low-cost adaptation alternative.