cs.CL（2024-09-03）

📊 共 20 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Leveraging Large Language Models for Solving Rare MIP Challenges 利用大语言模型解决罕见混合整数规划难题 large language model chain-of-thought
2 Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation Booster：通过衰减有害扰动应对大语言模型中的有害微调攻击 large language model ✅
3 AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models AdaComp：基于自适应预测器的抽取式上下文压缩，提升检索增强大语言模型效率 large language model
4 S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners 提出S^3c-Math，赋予大语言模型自发式步骤级数学推理自纠错能力 large language model
5 FuzzCoder: Byte-level Fuzzing Test via Large Language Model 提出FuzzCoder，利用微调大语言模型指导字节级模糊测试，提升漏洞发现效率。 large language model
6 Towards Leveraging Large Language Models for Automated Medical Q&A Evaluation 利用大语言模型自动评估医疗问答系统的响应 large language model
7 LLM-GAN: Construct Generative Adversarial Network Through Large Language Models For Explainable Fake News Detection 提出LLM-GAN以解决可解释假新闻检测问题 large language model
8 Interpreting and Improving Large Language Models in Arithmetic Calculation 揭示大语言模型算术计算机制，选择性微调提升数学能力 large language model
9 From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning 提出Pinpoint Tuning，解决大语言模型中的谄媚问题，提升真诚度。 large language model ✅
10 LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs LongGenBench：提出长文本生成评测基准，揭示现有LLM在长上下文任务中的不足 large language model instruction following
11 MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs 提出MMLU-Pro+以评估LLMs的高阶推理与捷径学习问题 large language model ✅
12 You Only Use Reactive Attention Slice For Long Context Retrieval 提出基于反应式注意力切片的YOURA长文本检索方法，提升LLM推理效率。 large language model
13 Training on the Benchmark Is Not All You Need 提出基于选项洗牌的数据泄露检测方法，评估LLM在基准测试中的数据泄露程度 large language model
14 Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study 提出PruningRAG框架，解决RAG中多源知识融合与噪声干扰问题，并构建基准数据集。 large language model ✅
15 Benchmarking Cognitive Domains for LLMs: Insights from Taiwanese Hakka Culture 构建客家文化认知基准，评估大型语言模型在文化理解和处理中的能力。 large language model
16 Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text Political DEBATE：高效的政治文本零样本与少样本分类器 large language model
17 Investigating Expert-in-the-Loop LLM Discourse Patterns for Ancient Intertextual Analysis 利用专家在环的大语言模型进行古代文本互文性分析 large language model
18 AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction 提出AgentRE框架，利用LLM解决复杂场景下的关系抽取难题 large language model ✅
19 An Implementation of Werewolf Agent That does not Truly Trust LLMs 提出结合LLM与规则的狼人杀Agent，提升对话一致性与逻辑性。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
20 Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs 提出自指令衍生提示生成框架，结合上下文学习提升黑盒LLM性能 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页