Signals 4 · free daily AI digest

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

Paper recorded by Signals 4 on 2026-09-23 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.LG · 机器学习 · first seen 2026-09-24

Abstract

Fine-tuning large language models on parallel data improves translation quality but can cause catastrophic forgetting. Mitigation methods are generally evaluated by retention on general benchmarks. We ask whether these findings transfer to machine translation (MT) fine-tuning and to MT-specific instruction following (MT-IF): instructions that modify a translation, such as formality, grammatical ge

Read on arXiv →

#10 most recent of 278 cs.LG papers we have recorded · ↑ newer: Memory Attention · ↓ older: Quantum score matching with applications to learning thermal states
Cite this page: Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following: the #10 most recent of 278 cs.LG papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/fine-tuning-llms-for-translation-general-forgetting-mitigation-does-not-preserve.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions