12 2024 档案
摘要:目的: reduce bias of LLMs(length, concreteness, empty reference, content continuation, nested instruction, familiar knowledge) Tool: OffsetBias: pairwis
阅读全文
摘要:Abstract 本文: Speculative RAG Task: improving retrieval results by combining RAG with LLMs refinement Method: 利用large Generalist LM大点的通用模型来验证RAG drafts
阅读全文
摘要:Abstract good words: subjectivity, variability, scale Task: Survey of LLM-as-a-Judge, benchmark & evaluation of LLM-as-a-Judge systems Core question:
阅读全文
摘要:Abstract Task: Defense LLM from prompt injection attacks Tool: TaskTracker Methods: use activation deltas( the difference in activations before and af
阅读全文
摘要:Abstract Github: https://github.com/JailbreakBench/jailbreakbench https://jailbreakbench.github.io/ Task: Opensource benchmark an evolving repository
阅读全文