5 papers · 1 filter
ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement
Xingbo Yao, Xiaoman Wang, Zhengwu Lei +11
Adapting general-purpose large language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is especially c…
When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation
Yiwen Qiu, Linjuan Wu, Dingming Li +7
Automatic translation quality metrics trained on general-domain corpora systematically fail on social media content, where communicative intent is encoded in culturally loaded expr…
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Haolong Qian, Xianliang Yang, Yinuo ma +6
Knowledge distillation from powerful reasoning models is widely used to improve Small Language Models (SLMs) on mathematical reasoning, often assuming that traces with higher rewar…
Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
Linjuan Wu, Ruiqi Zhang, Xinze Lyu +7
Social media platforms enable large-scale cross-lingual communication, but translating user-generated content (UGC) remains challenging due to its informal style, cultural referenc…
Unsupervised Text Style Transfer for Controllable Intensity
Shuhuan Gu, Wenbiao Tao, Xinchen Ma +4
Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between…