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. |
Similar Papers
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. |
Semi-Supervised Reward Modeling via Iterative Self-Training (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reward models capture values and preferences of humans and are used in Reinforcement Learning with Human Feedback (RLHF) Traditionally, training large language models relies on extensive human-annotated preference data, which poses significant challenges in terms of scalability and cost. |
| Approach: | They propose a method that enhances RM training using unlabeled data. |
| Outcome: | The proposed approach improves reward models without incurring additional labeling costs on unlabeled datasets. |
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge (2025.emnlp-main)
Copied to clipboard
Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E Weston, Sainbayar Sukhbaatar
| Challenge: | Existing methods for improving large language models have focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. |
| Approach: | They propose an iterative Meta-Rewarding step where the model judges its own judgements and uses that feedback to refine its judgment skills. |
| Outcome: | The proposed model improves Llama-3-8B-Instruct from 22.9% to 39.4% on AlpacaEval 2 and 20.6% to 29.1% on Arena-Hard. |
Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing Large Language Models (LLMs) struggle with novelty and Reinforcement Learning from human feedback (RLHF) is costly. |
| Approach: | They propose to use a Reward Model (RM) and a principle-guided LLM-as-a-Judge to enhance creative output over baselines. |
| Outcome: | The proposed approach significantly enhances creative output over baselines, but the principle-guided LLM-as-a-Judge yields superior generation quality. |
ReMedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Regression-based neural metrics struggle with inconsistency of human ratings . prompting large language models (LLMs) for MT scoring has also shown promise . |
| Approach: | They propose a MT metric framework that reformulates translation evaluation as a reward modeling task. |
| Outcome: | The proposed framework surpasses larger WMT winners and massive closed LLMs across 39 language pairs and 111 MT systems. |
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. |
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Empirical evaluations on eight recent LLMs reveal that DRPO significantly enhances alignment performance, enabling base models to outperform their SFT/RLHF-tuned counterparts. |
| Approach: | They propose a tuning-free approach to self-alignment called Dynamic Rewarding with Prompt Optimization (DRPO) it leverages a dynamic rewarding mechanism to identify and rectify alignment weaknesses . |
| Outcome: | The proposed approach outperforms existing methods and is highly adaptable to various alignment challenges. |
RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)
Copied to clipboard
Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang
| Challenge: | Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks. |
| Approach: | They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes. |
| Outcome: | The proposed training framework significantly improves upon translation baselines. |
Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch (2025.findings-emnlp)
Copied to clipboard
Yirong Zeng, Xiao Ding, Yutai Hou, Yuxian Wang, Li Du, Juyi Dai, Qiuyang Ding, Duyu Tang, Dandan Tu, Weiwen Liu, Bing Qin, Ting Liu
| Challenge: | Experimental results demonstrate that our models achieve over 7% performance improvement compared to both SFT and RL-with-SFT models under the same experimental settings. |
| Approach: | They propose a dynamic generalization-guided reward design for rule-based RL that shifts rewards from exploratory to exploitative tool-use patterns. |
| Outcome: | The proposed model achieves over 7% performance improvement compared to SFT and RL-with-SFT models under the same experimental settings. |
RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results demonstrate the superiority of our approach to aligning large language models with human preferences. |
| Approach: | They propose a method that evaluates and assigns specific credit to each token using an off-the-shelf reward model. |
| Outcome: | The proposed method evaluates and assigns specific credit to each token using an off-the-shelf reward model. |