8 papers
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
Pengrui Han, Xueqiang Xu, Keyang Xuan +12
Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely…
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang +13
Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retr…
Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi +31
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learnin…
Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models
Runchu Tian, Junxia Cui, Xueqiang Xu +2
Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) models, offering advantages such as accelerated parallel decoding an…
Zero-Shot Open-Schema Entity Structure Discovery
Xueqiang Xu, Jinfeng Xiao, James Barry +7
Entity structure extraction, which aims to extract entities and their associated attribute-value structures from text, is an essential task for text understanding and knowledge gra…
LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval
Yanzhen Shen, Sihao Chen, Xueqiang Xu +3
While significant progress has been made with dual- and bi-encoder dense retrievers, they often struggle on queries with logical connectives, a use case that is often overlooked ye…