2 papers
cs.AI2025
Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
Jiaqi Wei, Hao Zhou, Xiang Zhang +6
Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail t…
q-bio.BM2024
COMET: Benchmark for Comprehensive Biological Multi-omics Evaluation Tasks and Language Models
Yuchen Ren, Wenwei Han, Qianyuan Zhang +13
As key elements within the central dogma, DNA, RNA, and proteins play crucial roles in maintaining life by guaranteeing accurate genetic expression and implementation. Although res…