新闻
Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Fine-tuning LLMs on translation data causes catastrophic forgetting, and standard mitigation methods fail to preserve translation-specific instruction following like formality control.
- 为何重要
- Engineers building multilingual systems or adapting LLMs for machine translation need to understand trade-offs between general capability retention and translation task performance.
- 注意
- Elastic Weight Consolidation preserves general benchmarks but not translation-specific controls; data mixing works only on seen prompts and does not generalize to unseen variants.
- llm
- language model
- fine-tun
- eval
- benchmark
这条新闻背后的模式
- MAPS: Multilingual Agent Performance & Security
- Agent Context Preservation and Recovery
- GAIA: General AI Assistants Benchmark
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。