AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC

Linjuan Wu, Ruiqi Zhang, Xinze Lyu, Ye Guo, Daoxin Zhang, Zhe Xu, Yao Hu, Yixin Cao, Yongliang Shen, Weiming Lu

ICML 2026 · Large language models › Language, safety and interpretability · approach: Multilingual LLM data and culture · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune Qwen3-8B on JUDGER-refined UGC translation dataQwen3-8B · CULTURE-MTineffective share: 49.60% -> 14.47%; score-3 share 4.09% -> 28.24%Improved
fine-tune Qwen3-32B on JUDGER-refined UGC translation dataQwen3-32B · CULTURE-MTineffective share: 30.74% -> 13.97%Improved
add JUDGER-guided rewrite loop to training data construction (ablation)Ours-32B · CULTURE-MTineffective share: 16.87% -> 13.97%Improved
add JUDGER-guided rewrite loop to training data construction (ablation)Ours-8B · CULTURE-MTineffective share: 16.17% -> 14.47%Improved
scale base LLM size (Qwen3 0.6B to 32B)Qwen3 family · CULTURE-MTineffective share: 95.41% (0.6B) -> 30.74% (32B)Improved
use BLEU/ChrF/COMET instead of cultural effectiveness to compare scalesevaluation metrics · CULTURE-MTmetric discriminabilityNo clear effect
fine-tune JUDGER (Qwen3-32B SFT) vs prompted Qwen3-32BQwen3-32B judge · Judger validation setaccuracy: 78.05% -> 86.03%Improved
use translation-specialized Seed-X-PPO vs general Qwen3-32B-sized modelsSeed-X-PPO · CULTURE-MTaverage cultural score: 1.71 avg vs Qwen3-32B 1.73No clear effect
fine-tune Qwen3-8B on UGC data, evaluate on general FLORESQwen3-8B · FLORESBLEU / COMET: BLEU 58.06 -> 15.92; COMET 87.38 -> 84.47Hurt
increase symbol density and expressiveness of notes (General to Symbol/Hybrid)most models · CULTURE-MT note typesineffective shareHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy