cs.CL（2025-01-30）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models 提出自监督量化表示SSQR，实现知识图谱与大语言模型的无缝集成 large language model instruction following
2 Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction 评估LLM在纵向临床数据上的时序推理能力，用于病历总结和诊断预测 large language model chain-of-thought
3 Differentially Private Steering for Large Language Model Alignment 提出PSA算法，通过差分隐私指导LLM对齐，保护私有数据。 large language model
4 A Multi-Layered Large Language Model Framework for Disease Prediction 提出多层大语言模型框架，用于提升社交医疗场景下的疾病预测能力 large language model
5 Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models 利用大型语言模型从入侵生物学文献中挖掘物种、地点、栖息地和生态系统信息。 large language model
6 Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation Panacea：通过后微调扰动缓解大型语言模型的有害微调攻击 large language model ✅
7 Examining the Robustness of Large Language Models across Language Complexity 考察大语言模型在不同语言复杂度下的鲁棒性，聚焦学生写作文本分析场景。 large language model
8 Contextually Structured Token Dependency Encoding for Large Language Models 提出上下文结构化Token依赖编码，提升大语言模型生成序列的上下文连贯性。 large language model
9 Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models 提出MG-PTQ，利用图神经网络进行低比特大语言模型混合精度量化。 large language model
10 Statistical multi-metric evaluation and visualization of LLM system predictive performance 提出LLM系统性能统计评估与可视化框架，辅助系统配置决策。 large language model
11 Rope to Nope and Back Again: A New Hybrid Attention Strategy 提出混合注意力机制，提升长文本LLM在长短上下文任务中的性能与效率 large language model
12 Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs 针对o1类LLM推理过程中的“欠思考”问题，提出TIP解码策略。 large language model
13 Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch 提出流式DiLoCo算法，通过通信重叠显著降低分布式LLM训练的带宽需求。 large language model
14 RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects 提出RbFT，增强RAG系统在检索缺陷下的鲁棒性 large language model
15 Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking 利用LLM摘要提升众包事实核查效率与效果 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
16 CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering CALM：释放语言模型在跨语言问答中的自对齐能力 DPO direct preference optimization large language model
17 Diverse Preference Optimization 提出Diverse Preference Optimization (DivPO)，提升语言模型生成内容的多样性，同时保持生成质量。 reinforcement learning DPO instruction following

⬅️ 返回 cs.CL 首页 · 🏠 返回主页