mlsanityData to 7 Oct 2026

From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization

arXiv 2602.01068 ↗First posted 1 Feb 2026cs.CL cs.AIcited by 1

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 64 of its 87 references that are in the map. First posted on arXiv 1 Feb 2026.

Builds on

64 of 87 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025SDPO: Segment-Level Direct Preference Optimization for Social Agents3 Jan
  2. 2024TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights6 Oct
  3. 2024Direct Multi-Turn Preference Optimization for Language Agents21 Jun
  4. 2024SimPO: Simple Preference Optimization with a Reference-Free Reward23 May
  5. 2024Token-level Direct Preference Optimization18 Apr
  6. 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation16 Jan
  7. 2023A General Theoretical Paradigm to Understand Learning from Human Preferences18 Oct
  8. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 56

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2025Qwen3 Technical Reportcited by 8,195
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  7. 2024Qwen2.5 Technical Reportcited by 4,713
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  10. 2017Deep reinforcement learning from human preferencescited by 3,846
  11. 2020Learning to summarize from human feedbackcited by 2,562
  12. 2024A Survey on LLM-as-a-Judgecited by 1,384
38 more
  1. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  2. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  3. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  4. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  5. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  6. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  7. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  8. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  9. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  10. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  11. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  12. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 311
  13. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 260
  14. 2024ReFT: Reasoning with Reinforced Fine-Tuningcited by 236
  15. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 226
  16. 2024SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Modelscited by 225
  17. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 201
  18. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  19. 2020Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPOcited by 184
  20. 2023MADLAD-400: A Multilingual And Document-Level Large Audited Datasetcited by 180
  21. 2023Benchmarking Foundation Models with Language-Model-as-an-Examinercited by 172
  22. 2023Generative Judge for Evaluating Alignmentcited by 163
  23. 2017Interactive Learning from Policy-Dependent Human Feedbackcited by 155
  24. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
  25. 2024LLaVA-Critic: Learning to Evaluate Multimodal Modelscited by 132
  26. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignmentcited by 104
  27. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 89
  28. 2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 88
  29. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
  30. 2024Self-Taught Evaluatorscited by 70
  31. 2023CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generationcited by 65
  32. 2024From LLM to NMT: Advancing Low-Resource Machine Translation with Claudecited by 57
  33. 2023Data-Juicer: A One-Stop Data Processing System for Large Language Modelscited by 52
  34. 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoningcited by 49
  35. 2024A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontierscited by 39
  36. 2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
  37. 2020From Speech-to-Speech Translation to Automatic Dubbingcited by 25
  38. 2024How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMscited by 23

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Preference-driven Paradigm for Enhanced Translation with Large Language Models
  2. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
  3. 2024PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
  4. 2025Aligning Large Language Models to Low-Resource Languages through LLM-Based Selective Translation: A Systematic Study
  5. 2024Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis
  6. 2024Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
  7. 2025Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization
  8. 2022Bootstrapping Multilingual Semantic Parsers using Large Language Models