Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model

• URL: http://arxiv.org/abs/2401.12873v3
• Date: Mon, 18 Mar 2024 15:16:16 GMT
• Title: Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
• Authors: Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, Zhaopeng Tu,
• Abstract summary: In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training. We first identify the overoptimization problem during QE-based feedback training, manifested as an increase in reward while translation quality declines. To address the problem, we adopt a simple yet effective method that uses rules to detect the incorrect translations and assigns a penalty term to the reward scores of them.
• Score: 75.66013048128302
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation without reference, has achieved impressive alignment with human evaluations in the last two years. In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training. We first identify the overoptimization problem during QE-based feedback training, manifested as an increase in reward while translation quality declines. We examine the problem and argue that the vulnerability of the QE model might lead to high rewards for incorrect translations, resulting in overoptimization and error propagation. To address the problem, we adopt a simple yet effective method that uses heuristic rules to detect the incorrect translations and assigns a penalty term to the reward scores of them. Experimental results show that the proposed QE-based feedback training achieves consistent and significant improvements across various settings, further verified through human preference studies. Our subsequent analysis demonstrates the high data efficiency of the proposed QE-based feedback training: it outperforms systems using larger parallel corpora by a small amount of monolingual data. Our code is available at: https://github.com/zwhe99/FeedbackMT

Related papers

• Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs [25.011675414622392]
  This study introduces a novel approach to enhance the reward model's generalization ability against distribution shifts. We retain the base model's language model head and incorporate a suite of text-generation losses to preserve the hidden states' text-generation capabilities. Our experimental results demonstrate that the introduced regularization technique markedly improves the accuracy of learned reward models.
  arXiv  Detail & Related papers  (2024-06-14T17:49:59Z)
• Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution [57.42593422091653]
  We explore leveraging reinforcement learning with human feedback to improve translation quality. A reward model with strong language capabilities can more sensitively learn the subtle differences in translation quality.
  arXiv  Detail & Related papers  (2024-02-18T09:51:49Z)
• Aligning Neural Machine Translation Models: Human Feedback in Training and Inference [27.84975767573212]
  Reinforcement learning from human feedback (RLHF) is a technique to improve the quality of the text generated by a language model. In machine translation (MT), where metrics trained from human annotations can readily be used as reward models, methods using minimum Bayes risk decoding and reranking have succeeded in improving the final quality of translation.
  arXiv  Detail & Related papers  (2023-11-15T17:21:58Z)
• Constructive Large Language Models Alignment with Diverse Feedback [76.9578950893839]
  We introduce Constructive and Diverse Feedback (CDF) as a novel method to enhance large language models alignment. We exploit critique feedback for easy problems, refinement feedback for medium problems, and preference feedback for hard problems. By training our model with this diversified feedback, we achieve enhanced alignment performance while using less training data.
  arXiv  Detail & Related papers  (2023-10-10T09:20:14Z)
• Calibrating LLM-Based Evaluator [92.17397504834825]
  We propose AutoCalibrate, a multi-stage, gradient-free approach to calibrate and align an LLM-based evaluator toward human preference. Instead of explicitly modeling human preferences, we first implicitly encompass them within a set of human labels. Our experiments on multiple text quality evaluation datasets illustrate a significant improvement in correlation with expert evaluation through calibration.
  arXiv  Detail & Related papers  (2023-09-23T08:46:11Z)
• Iterative Translation Refinement with Large Language Models [25.90607157524168]
  We propose iteratively prompting a large language model to self-correct a translation. We also discuss the challenges in evaluation and relation to human performance and translationese.
  arXiv  Detail & Related papers  (2023-06-06T16:51:03Z)
• PreQuEL: Quality Estimation of Machine Translation Outputs in Advance [32.922128367314194]
  A PreQuEL system predicts how well a given sentence will be translated, without recourse to the actual translation. We develop a baseline model for the task and analyze its performance. We show that this augmentation method can improve the performance of the Quality-Estimation task as well.
  arXiv  Detail & Related papers  (2022-05-18T18:55:05Z)
• Non-Parametric Online Learning from Human Feedback for Neural Machine Translation [54.96594148572804]
  We study the problem of online learning with human feedback in the human-in-the-loop machine translation. Previous methods require online model updating or additional translation memory networks to achieve high-quality performance. We propose a novel non-parametric online learning method without changing the model structure.
  arXiv  Detail & Related papers  (2021-09-23T04:26:15Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Translation Error Detection as Rationale Extraction [36.616561917049076]
  We study the behaviour of state-of-the-art sentence-level QE models and show that explanations can indeed be used to detect translation errors. We introduce a novel semi-supervised method for word-level QE and (ii) propose to use the QE task as a new benchmark for evaluating the plausibility of feature attribution.
  arXiv  Detail & Related papers  (2021-08-27T09:35:14Z)

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.