mlsanityData to 14 Oct 2026

Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control

arXiv 2609.16967 ↗First posted 15 Sep 2026cs.CLcited by 0

On the map: Mechanistic interpretability → Activation steering methods

Abstract (arXiv)

Ensuring that multilingual language models generate coherent text in a specific target language is a major issue in multilingual language modeling. We develop an optimal control method for target-language text generation as well as a framework for evaluating the quality of generated text in terms of language adherence, linguistic coherence, and semantic coherence. We find that the proposed method performs at least as well as the prominent difference-in-means activation steering method for the majority of models tested, with substantially less hyperparameter tuning required.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability. Builds on 47 of its 60 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

47 of 60 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Steering Llama 2 via Contrastive Activation Addition9 Dec

Other references · 46

  1. 2024Qwen2.5 Technical Reportcited by 4,942
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  4. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  5. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  6. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
  7. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 712
  8. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  9. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
  10. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 417
  11. 2024Do Llamas Work in English? On the Latent Language of Multilingual Transformerscited by 281
  12. 2020Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?cited by 151
34 more
  1. 2024EuroLLM: Multilingual Language Models for Europecited by 106
  2. 2022The Geometry of Multilingual Language Model Representationscited by 95
  3. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 94
  4. 2020A Theoretical Analysis of the Repetition Problem in Text Generationcited by 83
  5. 2024On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neuronscited by 83
  6. 2025Do Multilingual LLMs Think In English?cited by 78
  7. 2024Understanding and Mitigating Language Confusion in LLMscited by 75
  8. 2024The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalitiescited by 69
  9. 2025Crosslingual Reasoning through Test-Time Scalingcited by 46
  10. 2024Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformerscited by 44
  11. 2025Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Modelscited by 44
  12. 2022Probing Classifiers are Unreliable for Concept Removal and Detectioncited by 41
  13. 2023Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspectivecited by 39
  14. 2020GRUEN for Evaluating Linguistic Quality of Generated Textcited by 37
  15. 2025The Bitter Lesson Learned from 2,000+ Multilingual Benchmarkscited by 31
  16. 2025ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfercited by 29
  17. 2024The Same But Different: Structural Similarities and Differences in Multilingual Language Modelingcited by 28
  18. 2024Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Interventioncited by 24
  19. 2024Repetition Neurons: How Do Language Models Produce Repetitions?cited by 23
  20. 2024Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMscited by 21
  21. 2025Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipelinecited by 21
  22. 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Languagecited by 21
  23. 2024LiSeCo: Linear Semantic Control for Language Generationcited by 20
  24. 2023Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similaritycited by 17
  25. 2025Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulationcited by 17
  26. 2026CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmarkcited by 12
  27. 2025Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Modelscited by 11
  28. 2025Improving Multilingual Language Models by Aligning Representations through Steeringcited by 11
  29. 2025The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMscited by 8
  30. 2022mOKB6: A Multilingual Open Knowledge Base Completion Benchmarkcited by 7
  31. 2025Cross-Lingual Generalization and Compression: From Language-Specific to Shared Neuronscited by 6
  32. 2025ReCoVeR the Target Language: Language Steering without Sacrificing Task Performancecited by 6
  33. 2025Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learningcited by 5
  34. 2025Language Surgery in Multilingual Large Language Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025In-Distribution Steering: Balancing Control and Coherence in Language Model Generation
  2. 2024Multi-property Steering of Large Language Models with Dynamic Activation Composition
  3. 2026Latent Mechanisms of Language Control in Multilingual Language Models
  4. 2026Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
  5. 2026Cross-Lingual Activation Steering for Multilingual Language Models
  6. 2025Steering When Necessary: Flexible Steering Large Language Models with Backtracking
  7. 2024Controllable Text Generation for Large Language Models: A Survey
  8. 2024Improving Instruction-Following in Language Models through Activation Steering