cs.CL（2024-12-06）

📊 共 25 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) (20 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale MAmmoTH-VL：通过大规模指令微调提升多模态大语言模型的推理能力 large language model multimodal
2 LLM-Align: Utilizing Large Language Models for Entity Alignment in Knowledge Graphs 提出LLM-Align，利用大语言模型解决知识图谱实体对齐问题 large language model instruction following
3 EXAONE 3.5: Series of Large Language Models for Real-world Use Cases LG AI研究院发布EXAONE 3.5系列大语言模型，提升真实场景指令遵循能力 large language model instruction following ✅
4 Foundation Models for Low-Resource Language Education (Vision Paper) 探讨LLM在低资源语言教育中的应用，助力社区驱动学习和数字化平台。 large language model foundation model
5 Explingo: Explaining AI Predictions using Large Language Models Explingo：利用大型语言模型将AI预测解释转化为自然语言叙述 large language model
6 QueEn: A Large Language Model for Quechua-English Translation QueEn：结合RAG与高效微调的克丘亚语-英语翻译大语言模型 large language model
7 A Practical Examination of AI-Generated Text Detectors for Large Language Models 评估AI生成文本检测器在大型语言模型中的有效性，揭示其在对抗攻击下的脆弱性。 large language model
8 Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies 提出基于探针分类器的视觉语言模型多模态事实核查方案，提升信息辨别能力。 multimodal
9 ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models ChatNVD：利用大型语言模型改进网络安全漏洞评估 large language model
10 Transformers Struggle to Learn to Search 研究表明Transformer在学习搜索能力上存在困难，并提出一种新颖的可解释性分析方法。 large language model chain-of-thought
11 CALICO: Conversational Agent Localization via Synthetic Data Generation CALICO：通过合成数据生成实现对话Agent的跨语言本地化 large language model
12 Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabase 利用psychNorms元数据库，系统评估文本、行为和脑数据语义表征的异同 large language model
13 Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern Ltri-LLM：一种免训练的动态三角注意力模式，用于LLM的流式长文本推理 large language model
14 Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications 提出并评估企业应用中基于GenAI的多智能体协作框架，提升任务完成效率。 large language model
15 BEExformer: A Fast Inferencing Binarized Transformer with Early Exits 提出BEExformer，一种结合二值化感知训练和早退机制的快速推理Transformer。 large language model
16 Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation 提出MuPaS多方对话微调框架，提升LLM在多人对话场景下的生成能力 large language model
17 100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo Acurai方法通过重塑查询与上下文数据，实现GPT模型RAGTruth任务中100%消除幻觉。 large language model
18 Evaluating and Aligning CodeLLMs on Human Preference 提出CodeArena基准和SynCode-Instruct数据集，提升代码大模型对人类偏好的对齐。 large language model
19 C$^2$LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation C$^2$LEVA：提出全面且无污染的大语言模型评测基准 large language model
20 Breaking Event Rumor Detection via Stance-Separated Multi-Agent Debate 提出S2MAD以解决社交媒体谣言检测问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
21 Large Language Models for Ingredient Substitution in Food Recipes using Supervised Fine-tuning and Direct Preference Optimization 利用监督微调和直接偏好优化，提出基于大语言模型的食谱配料替换方法 DPO direct preference optimization large language model
22 KaLM: Knowledge-aligned Autoregressive Language Modeling via Dual-view Knowledge Graph Contrastive Learning KaLM：通过双视角知识图谱对比学习对齐知识的自回归语言模型 contrastive learning large language model
23 DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling 提出DEMO以解决对话系统建模不足的问题 imitation learning large language model
24 Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning UniEA：提出统一双空间嵌入的实体对齐方法，通过对比学习提升性能。 contrastive learning ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
25 Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Games 提出Murder Mystery Agents框架，提升多智能体对话控制 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页