mlsanityData to 14 Oct 2026

Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement

arXiv 2610.15661 ↗First posted 11 Oct 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Feedback presentation shapes how LLMs use evaluator judgments during translation refinement. We introduce a machine translation protocol that keeps the evaluator score, main issue, and recommendation fixed while varying feedback form and supporting detail. Across seven models and six translation directions, low-load feedback outperforms high-load feedback in all 42 translator-direction settings under xCOMET. On the 29,400-record rewriting subset, mean xCOMET scores multiplied by 100 are 83.30 for low-load feedback and 80.67 for high-load feedback; the full-matrix original-translation reference mean is 83.46. MetricX-24 supports the low-load advantage on a stratified subset. A no-feedback second pass yields a small improvement over the original translations, and direct evaluator prompting reproduces the low-load advantage without a separate rewriting stage. These results show that compact feedback limits the quality loss from evaluator-guided refinement in the evaluated high-resource MT settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 11 Oct 2026.

Builds on

22 of 33 references.

References · 22

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  5. 2023Teaching Large Language Models to Self-Debugcited by 988
  6. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  7. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  8. 2018AI safety via debatecited by 400
  9. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  10. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  11. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
  12. 2021To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translationcited by 163
10 more
  1. 2025Multiagent Finetuning: Self Improvement with Diverse Reasoning Chainscited by 95
  2. 2024MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Taskcited by 93
  3. 2023LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scorescited by 90
  4. 2024MALT: Improving Reasoning with Multi-Agent LLM Trainingcited by 76
  5. 2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningcited by 41
  6. 2024SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responsescited by 26
  7. 2025Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agentscited by 24
  8. 2024PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluationcited by 16
  9. 2024Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandemcited by 9
  10. 2025Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Promptscited by 4

Built on by

Not cited yet.