Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

arXiv:2609.28395 · cs.CL, cs.LG · Submitted 2026-09-23 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• Fine-Tuning — 43× in this paper · explained in 5 episodes
• Benchmark — 33× in this paper · explained in 2 episodes
• alpha — 13× in this paper · explained in 1 episode
• Accuracy — 9× in this paper · explained in 1 episode
• Adaptation — 5× in this paper · explained in 1 episode
• Catastrophic Forgetting — 5× in this paper · explained in 5 episodes
• Commentary — 4× in this paper · explained in 2 episodes
• Elastic Weight Consolidation — 4× in this paper
• Perplexity — 4× in this paper · explained in 3 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Continual Learning — 3× in this paper · explained in 2 episodes
• Model Merging — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Fisher Information — 2× in this paper · explained in 3 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Selective Token Masking — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment Tax — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Confident Conflict Masking — 1× in this paper
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Entropy-Adaptive Fine-Tuning — 1× in this paper
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Selective Projection Decay — 1× in this paper
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
• RL Forgets! Towards Continual Policy Optimization
• IFMTBench: A Comprehensive Benchmark for Multilingual Translation Instruction Following
• Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
• Instruction-Following Evaluation for 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