The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space

arXiv:2609.00515 · cs.CL, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-01

Updated: 2026-09-01

Comments: 21 pages, 15 figures, 11 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fine-Tuning — 37× in this paper · explained in 5 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Ablation — 8× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Perplexity — 7× in this paper · explained in 3 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Cross-lingual Transfer — 4× in this paper · explained in 2 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Sparsity — 4× in this paper · explained in 4 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Activation Patching — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• LoRA Fine-Tuning — 2× in this paper · explained in 3 episodes
• Low-Resource Languages — 2× in this paper · explained in 4 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Beyond English-Centric Multilingual Machine Translation
• How to use and interpret activation patching
• How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
• ChatGPT MT: Competitive for High- (but not Low-) Resource Languages
• Activation Steering via Generative Causal Mediation
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Attribution Patching Outperforms Automated Circuit Discovery
• Function Vectors in Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering