cs.CL（2024-08-30）

📊 共 15 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data 提出一种基于损坏的 grounding 数据预训练的多模态幻觉检测方法，提升样本效率。 multimodal
2 Enhancing Event Reasoning in Large Language Models through Instruction Fine-Tuning with Semantic Causal Graphs 提出基于语义因果图指令微调的大语言模型事件推理方法，显著提升事件检测性能。 large language model
3 Can Large Language Models Address Open-Target Stance Detection? 提出开放目标立场检测（OTSD）任务，并评估大型语言模型（LLMs）的性能。 large language model
4 The creative psychometric item generator: a framework for item generation and validation using large language models 提出创造性心理测量项目生成器（CPIG），利用大语言模型自动生成并验证创造力评估试题。 large language model
5 Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMs 提出定义增强的启发式驱动提示方法(DHP)，以提升LLM在文档级事件论元抽取任务上的性能。 large language model chain-of-thought
6 LLMs Prompted for Graphs: Hallucinations and Generative Capabilities 探究LLM在图谱任务中的幻觉与生成能力，揭示其涌现特性与局限性 large language model
7 Dynamic Depth Decoding: Faster Speculative Decoding for LLMs 提出动态深度解码DDD，加速LLM推断，提升EAGLE-2速度44%。 large language model
8 MemLong: Memory-Augmented Retrieval for Long Text Modeling MemLong：提出一种基于记忆增强检索的长文本建模方法，显著扩展LLM的上下文处理能力。 large language model ✅
9 Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content 提出IBIS指标，结合认知模型与LLM嵌入，提升人类主观相似度衡量 large language model
10 Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain 评估生成式语言模型在气候变化领域分类任务中的性能与自评估能力 large language model
11 Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning 提出Novel-WD数据集，探索Prefix-Tuning在LLM中学习新世界知识的能力 large language model
12 Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios 提出工具辅助Agent框架，解决Text-to-SQL中真实场景下的数据库不匹配问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
13 MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models 提出MultiMath以解决视觉与数学推理整合问题 reinforcement learning large language model multimodal ✅
14 MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models MaFeRw：融合多方面反馈的查询重写方法，提升检索增强大语言模型性能 reinforcement learning PPO large language model
15 Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback 提出序列到序列奖励建模，通过语言反馈提升RLHF对齐效果 reinforcement learning RLHF large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页