cs.CL（2024-08-19）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation Anim-Director：基于大型多模态模型的可控动画视频生成Agent multimodal
2 Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models 提出MLNeedle基准测试，评估多语言大模型在长文本中信息检索能力。 large language model
3 Performance Law of Large Language Models 提出“性能定律”，通过少量超参数精确预测大语言模型的MMLU得分。 large language model
4 IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction 提出IDEA框架，提升大语言模型Agent在交互环境中基于归纳、演绎和溯因的规则学习能力 large language model
5 MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models MegaFake：提出基于大语言模型和社交心理学理论的假新闻生成与检测数据集 large language model
6 Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving 提出检索增强翻译方法RAT，提升大语言模型在古诗翻译中的质量与诗意。 large language model
7 Importance Weighting Can Help Large Language Models Self-Improve 提出基于重要性权重的LLM自提升方法，有效过滤高分布偏移样本。 large language model
8 CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models 提出CMoralEval基准以评估中文大语言模型的道德表现 large language model ✅
9 Beyond Relevant Documents: A Knowledge-Intensive Approach for Query-Focused Summarization using Large Language Models 提出一种知识密集型查询聚焦摘要方法，解决传统方法依赖相关文档的局限性。 large language model
10 Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence? 对比研究LLM概率置信度和语言置信度，揭示知识边界感知的差异与联系 large language model
11 Value Alignment from Unstructured Text 提出一种基于非结构化文本的LLM价值观对齐方法，降低对监督数据的依赖。 large language model
12 ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA ELDER：利用混合LoRA增强终身模型编辑能力，解决知识遗忘问题。 large language model ✅
13 X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents X-TURING：面向长期对话Agent的增强型高效图灵测试 large language model
14 How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments 利用提示工程提升大型语言模型在可接受性判断任务中的语法知识评估 large language model
15 Resolving Lexical Bias in Model Editing 提出PENME以解决模型编辑中的词汇偏见问题 large language model
16 Instruction Finetuning for Leaderboard Generation from Empirical AI Research 利用指令微调大型语言模型自动生成AI研究排行榜 large language model
17 Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory 提出基于上下文完整性理论的隐私检查清单，利用LLM检测隐私泄露。 large language model
18 Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer 提出基于神经投影的零样本跨语言迁移方法，提升LLM多语言代码生成能力 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🔗⭐
19 Continual Dialogue State Tracking via Reason-of-Select Distillation 提出基于选择理由蒸馏的持续对话状态跟踪方法，解决灾难性遗忘和值选择难题。 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页