自然语言处理
28 篇 · 资讯流Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suff
原文 ↗VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs
原文 ↗Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell
Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evide
原文 ↗Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs
Clinical questions often depend on linking a patient's multimodal evidence to external biomedical knowledge, yet existin
原文 ↗CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning
Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-trainin
原文 ↗Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning
Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time b
原文 ↗A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with c
原文 ↗$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient
LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that
原文 ↗Self-Adapting Group of Experts for Multi-Agent Reasoning
Multi-agent systems bring together language model agents with different roles to propose, review, and refine solutions.
原文 ↗Jailbreaks for Black-Box Uncertainty Quantification in Large Reasoning Models
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces s
原文 ↗