Challenge: Reinforcement Learning (RL) is dependent on the reward formulation due to the intrinsic difficulty of the task in the high-dimensional discrete action space and the sparseness of the standard reward functions.
Approach: They propose a maximally dense semantic-level unsupervised reward function which mimics human evaluation by considering both sentence fluency and semantic similarity.
Outcome: The proposed reward outperforms the standard sparse reward by 2% on average for in- and out-of-domain settings.

Similar Papers

Exploring Supervised and Unsupervised Rewards in Machine Translation (2021.eacl-main)

Copied to clipboard

Challenge: Autoregressive sequence-to-sequence (seq2sequ) neural architectures have become the de facto approach in Machine Translation (MT).
Approach: They propose to make models less reliant on cross-entropy loss and evaluation metrics . they propose an entropicity-regularised RL method that explores the action space .
Outcome: The proposed method exploits the action space and unsupervised reward function to balance between exploration and exploitation.
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Large-scale reinforcement learning (RL) methods have proven effective in enhancing the reasoning abilities of large language models.
Approach: They propose an open-source adaptation of the R1-Zero RL framework for machine translation (MT) their code is available at https://github.com/fzp0424/MT-R1-zero.
Outcome: The proposed framework surpasses towerinstruct-7B-v0.2 on the english-chinese benchmark by 1.26 points.
Reinforcement Learning with Large Action Spaces for Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Recent work has argued that the gains produced by Reinforcement learning are mostly due to promoting tokens that have already received a fairly high probability in pre-training.
Approach: They hypothesize that the large action space is a main obstacle to RL’s effectiveness in MT by reducing the size of the vocabulary without changing the vocabulary.
Outcome: The proposed method improves by 1.5 BLEU points on average.
Breaking Consensus Bias: Unsupervised Reinforcement Learning for Machine Translation (2026.findings-acl)

Copied to clipboard

Challenge: Existing RL approaches for MT face fixed references or the production of homogeneous references leading to mode collapse in unsupervised settings.
Approach: They propose an Entropy-Driven Unsupervised RL framework for machine translation that leverages entropy for supervision construction and self-evolution.
Outcome: The proposed framework outperforms supervised and unsupervised baselines in multiple language pairs.
SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable capabilities in machine translation, but most MT-specific LLMs rely heavily on external supervision during training.
Approach: They propose a reinforcement learning framework for machine translation that is reference-free and relies solely on self-judging rewards.
Outcome: The proposed framework outperforms existing LLMs and larger general LLM models on English Chinese translation benchmarks and performs competitively with leading closed-source systems.
A Study of Reinforcement Learning for Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation systems.
Approach: They propose to leverage reinforcement learning to boost the performance of NMT systems trained with monolingual data.
Outcome: The proposed method achieves competitive results on translation tasks in English-German, Chinese-English and English-English systems.
Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings (2026.tacl-1)

Copied to clipboard

Challenge: Reinforcement learning (RL) is an effective and robust method for training neural machine translation systems.
Approach: They propose a method that leverages fine-grained, token-level quality assessments . they use a state-of-the-art quality estimation system as their token- level reward model .
Outcome: The proposed approach leverages fine-grained, token-level quality assessments along with error severity levels to improve translation quality.
Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have yielded remarkable performance, but objective mismatch issues hinder RLHF learning.
Approach: They propose a Reinforcement Learning framework enhanced with Label-sensitive reward to enhance LLMs' alignment and generation capabilities.
Outcome: The proposed framework improves performance on five diverse models across eight tasks.
From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models (2025.emnlp-main)

Copied to clipboard

Challenge: Current research on long-form context in Large Language Models (LLMs) focuses on understanding of long-contexts, but the open-ended Long Text Generation (Open-LTG) remains underexplored.
Approach: They propose a method that uses data synthesis and a reward signal to enhance model performance.
Outcome: The proposed method outperforms GPT-4-Turbo and improves performance by 20% on the Open-LTG task.
VEG: Verbal 𝜖-greedy for Semantic Exploration in Multi-Turn RL Agents (2026.acl-industry)

Copied to clipboard

Challenge: Standard RL approaches suffer from reward sparsity and mode-seeking behavior . lack of diversity hinders exploration necessary for optimal learning .
Approach: They propose a framework that leverages external feedback as a dynamic control variable to explicitly balance exploration and exploitation within the semantic space.
Outcome: Experiments on Tau Bench and SearchQA show that the proposed framework outperforms standard RL baselines.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations