5 papers
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
Jianghan Shen, Siqi Luo, Xinyu Cheng +6
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for training agentic retrieval-augmented generation (RAG) systems from outcome-only superv…
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
ShiYing Huang, Liang Lin, Yuer Li +6
In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tensi…
SCRum-9: Multilingual Stance Classification over Rumours on Social Media
Yue Li, Jake Vasilakes, Zhixue Zhao +1
We introduce SCRum-9, the largest multilingual Stance Classification dataset for Rumour analysis in 9 languages, containing 7,516 tweets from X. SCRum-9 goes beyond existing stance…
It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
Yue Li, Zhixue Zhao, Carolina Scarton
Extremely low-resource languages, especially those written in rare scripts, as shown in Figure 1, remain largely unsupported by large language models (LLMs). This is due in part to…
Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models
Yue Li, Zhixue Zhao, Carolina Scarton
In-context learning (ICL) performance is highly sensitive to prompt design, yet the impact of class label options (e.g. lexicon or order) in zero-shot classification remains undere…