Tag
Tsinghua University and WuWenXinQiong teams have open-sourced a paper introducing C2C, a method for direct communication between large language models via cache fusion, eliminating text intermediaries to boost inference speed and accuracy significantly.
This paper proposes a task-based evaluation methodology for measuring semantic preservation in ontology learning, comparing LLM performance on source documents versus transformed representations in the legal domain.
Researchers propose HSPD, a corpus-level detoxification pipeline that rewrites toxic spans in pretraining data while preserving semantics, achieving state-of-the-art toxicity reduction on GPT-2 XL, LLaMA-2, OPT, and Falcon models.