Tag: Adaptive Systems
All the articles with the tag "Adaptive Systems".
-
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
ASTRA introduces an efficient defense for Vision Language Models by adaptively steering activations away from adversarial directions using image attribution, achieving state-of-the-art performance in mitigating jailbreak attacks with minimal impact on benign utility and high inference efficiency.
-
ThinkSwitcher: When to Think Hard, When to Think Fast
ThinkSwitcher通过一个轻量级自适应框架,使单一大型推理模型根据任务复杂性动态切换长短链式推理模式,在数学推理基准上减少20-30%计算成本,同时在复杂任务上保持较高准确率。
-
AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models
本文提出AdaptMI和AdaptMI+自适应方法,通过基于奖励模型检测问题难度并针对困难问题选择技能-based in-context示例,提高小语言模型在数学推理任务中的性能,同时避免认知过载。
-
LLM-Independent Adaptive RAG: Let the Question Speak for Itself
This paper introduces LLM-independent adaptive retrieval using 27 external information features across 7 groups, achieving comparable QA performance to LLM-based methods on 6 datasets while significantly improving efficiency by eliminating additional LLM calls during inference.
-
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
本文提出PLAN-AND-ACT框架,通过分离规划和执行模块、利用合成数据训练和动态重规划,提高LLM代理在复杂长期任务中的性能,并在web导航基准上达到state-of-the-art结果。