4 papers · 1 filter
Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training
Linjuan Wu, Yiwen Qiu, Xinze Lyu +11
Social media translation requires preserving meaning while capturing the cultural nuances of user-generated content (UGC). However, gaps in the cultural knowledge of LLM-based eval…
Vela: User Behavior as Supervision Sparks LLM Intelligence
Yang Xiao, Yusong Sun, Haoyi Wu +17
Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems.…
AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution
AllSpark Team, Shijun Wan, Jiancong Xie +8
Rule-governed contextual decision tasks require models to apply specified rules to case-specific context and evidence. Written rules can leave gaps in decision guidance and process…
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Haoyi Wu, Yang Xiao, Yusong Sun +4
Real-world tasks often require large language models (LLMs) to learn from complex task-specific context rather than pretrained parametric knowledge. This capability remains a weakn…