Retrieval-Augmented Generation (RAG) relies critically on the effectiveness of its retrieval component. Dense retrieval with Approximate Nearest Neighbor (ANN) search is efficient but relies on symmetric similarity metrics that can limit the modeling of directional relevance. Generative retrieval addresses this limitat...
Yifei Zhang, Hao Zhu, Haoran Shi et al.· Proceedings of the 32nd ACM...· 0 citations
The Reflective Cognitive Alignment (RCA) framework models stimulation interactions as a sequential decision process, integrating Protocol-Constrained Chain-of-Cognition (PC-CoC) for structured reasoning and Inference-Time Value Alignment (IVA) for principled response selection based on safety and engagement goals.
Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content. Blanket refusal discards valid evidence, whereas uncritical adoption yields incorrect or unsafe answers. The ability to selectively adopt relevant information while...
Yanyu Chen, Yue Li, Yongyi Cui et al.· arXiv.org· 1 citation
This work proposes eXtreme Gradient Boosting LoRA (XGBLoRA), a novel framework grounded in gradient boosting theory that provides theoretical analysis establishing convergence guarantees and expressiveness bounds, which formally justify why weaker (lower-rank) adapters, when properly combined, can match or exceed the p...
Yifei Zhang, Hao Zhu, Haoran Shi et al.· Proceedings of the 32nd ACM...· 0 citations
The Context Compilation Architecture (CCA), whose central novelty is a typed intermediate representation (IR) with fixed slots (rules.{must_do, must_not, conditional}, output_spec, available_tools, data_profile) into which any prose context is compiled once; executable verifiers and a violation-gated correction loop fo...
Jin-Hu Qi, Min-Da Hu, Wen-Tao Zhang et al.· 0 citations
Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource requirements. Low-Rank Adaptation (LoRA) has emerged as a promising solution, yet...
Yifei Zhang, Hao Zhu, Haoran Shi et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
