RIEQE is a two-stage SFT-then-RLVR framework that lets LRMs co-evolve implicit and explicit reasoning to surpass baselines on WMT fine-grained QE tasks.
Excl.” (self-exclusion, main protocol) and “Incl
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Human reference summaries outperform LLM outputs in informativeness, faithfulness, and factuality, while LLMs lead only in fluency and coherence, indicating summarization remains an open problem.
citing papers explorer
-
Unlocking Fine-Grained Translation Quality Estimation in LRMs through Synergistically Evolving Implicit and Explicit Reasoning
RIEQE is a two-stage SFT-then-RLVR framework that lets LRMs co-evolve implicit and explicit reasoning to surpass baselines on WMT fine-grained QE tasks.
-
Summarization is Not Dead Yet
Human reference summaries outperform LLM outputs in informativeness, faithfulness, and factuality, while LLMs lead only in fluency and coherence, indicating summarization remains an open problem.