Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation

• URL: http://arxiv.org/abs/2410.13944v1
• Date: Thu, 17 Oct 2024 18:09:43 GMT
• Title: Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation
• Authors: Junhong Wu, Yang Zhao, Yangyifan Xu, Bing Liu, Chengqing Zong,
• Abstract summary: Large Language Models (LLMs) have achieved impressive results across numerous NLP tasks but still encounter difficulties in machine translation. We propose a novel approach called RaDis (Rationale Distillation) to overcome this issue. RaDis harnesses the strong generative capabilities of LLMs to create rationales for training data, which are then "replayed" to prevent forgetting.
• Score: 31.733890798723085
• License:
• Abstract: Large Language Models (LLMs) have achieved impressive results across numerous NLP tasks but still encounter difficulties in machine translation. Traditional methods to improve translation have typically involved fine-tuning LLMs using parallel corpora. However, vanilla fine-tuning often leads to catastrophic forgetting of the instruction-following capabilities and alignment with human preferences, compromising their broad general abilities and introducing potential security risks. These abilities, which are developed using proprietary and unavailable training data, make existing continual instruction tuning methods ineffective. To overcome this issue, we propose a novel approach called RaDis (Rationale Distillation). RaDis harnesses the strong generative capabilities of LLMs to create rationales for training data, which are then "replayed" to prevent forgetting. These rationales encapsulate general knowledge and safety principles, acting as self-distillation targets to regulate the training process. By jointly training on both reference translations and self-generated rationales, the model can learn new translation skills while preserving its overall general abilities. Extensive experiments demonstrate that our method enhances machine translation performance while maintaining the broader capabilities of LLMs across other tasks. This work presents a pathway for creating more versatile LLMs that excel in specialized tasks without compromising generality and safety.

Related papers

• MoExtend: Tuning New Experts for Modality and Task Extension [61.29100693866109]
  MoExtend is an effective framework designed to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. MoExtend seamlessly integrates new experts into pre-trained MoE models, endowing them with novel knowledge without the need to tune pretrained models.
  arXiv  Detail & Related papers  (2024-08-07T02:28:37Z)
• TasTe: Teaching Large Language Models to Translate through Self-Reflection [82.83958470745381]
  Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. We propose the TasTe framework, which stands for translating through self-reflection. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T17:21:21Z)
• Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts [10.929547354171723]
  This paper introduces Knowledgeable Agents from Language Model Rollouts (KALM) It extracts knowledge from large language models (LLMs) in the form of imaginary rollouts that can be easily learned by the agent through offline reinforcement learning methods. It achieves a success rate of 46% in executing tasks with unseen goals, substantially surpassing the 26% success rate achieved by baseline methods.
  arXiv  Detail & Related papers  (2024-04-14T13:19:40Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models [56.25156596019168]
  This paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for large language models (LLMs) Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
  arXiv  Detail & Related papers  (2023-11-30T03:59:31Z)
• Orthogonal Subspace Learning for Language Model Continual Learning [45.35861158925975]
  O-LoRA is a simple and efficient approach for continual learning in language models. Our method induces only marginal additional parameter costs and requires no user data storage for replay.
  arXiv  Detail & Related papers  (2023-10-22T02:23:44Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• Pre-training Text-to-Text Transformers for Concept-centric Common Sense [48.11844351407072]
  We propose a concept-aware language model (CALM) to augment pre-trained language models with concept-centric commonsense knowledge. We show that CALM can pack more commonsense knowledge into the parameters of a pre-trained text-to-text transformer without relying on external knowledge graphs.
  arXiv  Detail & Related papers  (2020-10-24T07:00:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.