mlsanityData to 7 Oct 2026

TIM: Teaching Large Language Models to Translate with Comparison

arXiv 2307.04408 ↗First posted 10 Jul 2023cs.CLcited by 50

Not on the map. Why?

Abstract (arXiv)

Open-sourced large language models (LLMs) have demonstrated remarkable efficacy in various tasks with instruction tuning. However, these models can sometimes struggle with tasks that require more specialized knowledge such as translation. One possible reason for such deficiency is that instruction tuning aims to generate fluent and coherent text that continues from a given instruction without being constrained by any task-specific requirements. Moreover, it can be more challenging for tuning smaller LLMs with lower-quality training data. To address this issue, we propose a novel framework using examples in comparison to teach LLMs to learn translation. Our approach involves presenting the model with examples of correct and incorrect translations and using a preference loss to guide the model's learning. We evaluate our method on WMT2022 test sets and show that it outperforms existing methods. Our findings offer a new perspective on fine-tuning LLMs for translation tasks and provide a promising solution for generating high-quality translations. Please refer to Github for more details: https://github.com/lemon0830/TIM.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 10 Jul 2023.

Builds on

24 of 36 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  10. 2020Learning to summarize from human feedbackcited by 2,562
  11. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  12. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
12 more
  1. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
  2. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  3. 2022In-context Examples Selection for Machine Translationcited by 172
  4. 2023Multilingual Machine Translation with Large Language Models: Empirical Results and Analysiscited by 156
  5. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  6. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  7. 2023BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Modelscited by 42
  8. 2023ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedbackcited by 34
  9. 2022UniTE: Unified Translation Evaluationcited by 28
  10. 2021Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translationcited by 20
  11. 2016Bridging Neural Machine Translation and Bilingual Dictionariescited by 18
  12. 2023Chain-of-Dictionary Prompting Elicits Translation in Large Language Modelscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 30; 2025: 9; 2026: 1.

50 papers.

Sort:

By area:

  1. 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translationcited by 390
  2. 2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 88
  3. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 49
  4. 2024TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinementcited by 37
  5. 2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
  6. 2023Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrationscited by 34
  7. 2024SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflectioncited by 34
  8. 2024G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translationcited by 29
  9. 2023Improving Translation Faithfulness of Large Language Models via Augmenting Instructionscited by 28
  10. 2023Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuningcited by 28
  11. 2023Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decodingcited by 28
  12. 2024TasTe: Teaching Large Language Models to Translate through Self-Reflectioncited by 27
38 more
  1. 2024DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memorycited by 27
  2. 2024The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilitiescited by 22
  3. 2024Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Modelscited by 22
  4. 2024Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?cited by 16
  5. 2024Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classificationcited by 16
  6. 2024Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Levelcited by 11
  7. 2024Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuningcited by 11
  8. 2025Lost in Literalism: How Supervised Training Shapes Translationese in LLMscited by 11
  9. 2023Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decodingcited by 10
  10. 2023Simultaneous Machine Translation with Large Language Modelscited by 9
  11. 2024A Preference-driven Paradigm for Enhanced Translation with Large Language Modelscited by 9
  12. 2024Language Generation with Strictly Proper Scoring Rulescited by 8
  13. 2024AnyTrans: Translate AnyText in the Image with Large Scale Modelscited by 8
  14. 2024Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translationcited by 8
  15. 2025Just Go Parallel: Improving the Multilingual Capabilities of Large Language Modelscited by 8
  16. 2023On-the-Fly Fusion of Large Language Models and Machine Translationcited by 5
  17. 2024Towards Boosting Many-to-Many Multilingual Machine Translation with Large Language Modelscited by 5
  18. 2024Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attackscited by 5
  19. 2024Context-aware and Style-related Incremental Decoding framework for Discourse-Level Literary Translationcited by 5
  20. 2023Beyond MLE: Convex Learning for Text Generationcited by 4
  21. 2024Conversational SimulMT: Efficient Simultaneous Translation with Large Language Modelscited by 4
  22. 2024Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Taskcited by 4
  23. 2023SCALE: Synergized Collaboration of Asymmetric Language Translation Enginescited by 3
  24. 2024A Novel Paradigm Boosting Translation Capabilities of Large Language Modelscited by 3
  25. 2024Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuningcited by 3
  26. 2024forallutoexistsval: Autonomous Assessment of LLMs in Formal Synthesis and Interpretation Taskscited by 3
  27. 2025CRPO: Confidence-Reward Driven Preference Optimization for Machine Translationcited by 3
  28. 2025DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translationcited by 3
  29. 2025M2PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translationcited by 3
  30. 2024InstaTrans: An Instruction-Aware Translation Framework for Non-English Instruction Datasetscited by 2
  31. 2024CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Modelscited by 2
  32. 2024Sing it, Narrate it: Quality Musical Lyrics Translationcited by 2
  33. 2024LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translationcited by 1
  34. 2025The Effect of Language Diversity When Fine-Tuning Large Language Models for Translationcited by 1
  35. 2026STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translationcited by 1
  36. 2025Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoringcited by 0
  37. 2025AutoICE: Automatically Synthesizing Verifiable C Code via LLM-driven Evolutioncited by 0
  38. 2025A First-Order Logic-Based Alternative to Reward Models in RLHFcited by 0