Unlocking Fine-Grained Translation Quality Estimation in LRMs through Mutually Boosting Implicit and Explicit Reasoning

arXiv:2605.31378 · cs.CL · Submitted 2026-05-29 · Read on arXiv

cs.CL

Submitted: 2026-05-29

Updated: 2026-09-08

Comments: EMNLP 2026

Code: https://github.com/google/wmt-mqm-human-evaluation

License: http://creativecommons.org/licenses/by/4.0/

The gist: Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains.

Terminology

Abstract

Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that LRMs already possess strong multilingual capabilities, while the core challenge stems from the intrinsic difficulty of learning the fine-grained QE task. In this paper, we propose RIEQE (R easoning both I mplicitly and E xplicitly for QE), a simple two-stage training framework that enables the mutually boosting of implicit (layer-wise) and explicit (token-wise) reasoning capabilities. To make implicit reasoning feasible, we first decompose the complex QE task into straightforward subtasks. Based on this, our two-stage approach applies: (1) NonThinking-SFT, Supervised Fine-Tuning (SFT) without reasoning chains to directly boost the model's implicit reasoning tendency and capability; and (2) Thinking-RLVR, standard Reinforcement Learning with Verifiable Reward (RLVR) to subsequently strengthen explicit reasoning. On the WMT test sets, RIEQE based on Qwen3-4B-Thinking-2507 surpasses all baselines in explicit reasoning performance, while its implicit reasoning capability is also comparable to the best current encoder-based models. We further provide evidence for the mutually boosting between implicit and explicit reasoning, showing how they benefit each other in a bidirectional manner.

Sources

Related papers