Scaling Attention Head Analysis via Gradient-Based Attribution in Context-Aware Machine Translation

arXiv:2609.28117 · cs.CL, cs.AI · Submitted 2026-09-23 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-23

Updated: 2026-09-23

Code: https://github.com/mjpost/sacrebleu

Terminology

• Accuracy — 49× in this paper · explained in 1 episode
• Transformer — 24× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 9× in this paper
• Interpretability — 8× in this paper · explained in 15 episodes
• Indirect Object Identification — 7× in this paper
• Generalizability — 5× in this paper · explained in 6 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• In Context-Aware Machine Translation — 3× in this paper
• Normalized Discounted Cumulative Gain — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Attention Mechanism — 2× in this paper · explained in 2 episodes
• Transformer Architecture — 2× in this paper · explained in 2 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Identifying and Controlling Important Neurons in Neural Machine Translation
• Does Neural Machine Translation Benefit from Larger Context?
• A baseline revisited: Pushing the limits of multi-segment models for context-aware translation
• In-context Learning and Induction Heads
• Escaping the sentence-level paradigm in machine translation
• Qwen2.5 Technical Report
• EuroLLM-22B: Technical Report
• Gemma 3 Technical Report
• Adapting Large Language Models for Document-Level Machine Translation
• Qwen2 Technical Report

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