cs.CL（2024-02-17）

📊 共 26 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) (24 🔗4) 支柱一：机器人控制 (Robot Control) (1) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models 提出Boosting of Thoughts框架以提升大语言模型的复杂问题求解能力 large language model chain-of-thought
2 Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction 提出REPaL以解决零-shot关系抽取中的标注需求问题 large language model
3 Contrastive Instruction Tuning 提出对比指令调优以解决LLM对未见指令的鲁棒性问题 large language model ✅
4 Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs 提出链式推理评估方法以解决多跳问答中的知识图谱问题 large language model chain-of-thought
5 A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models 提出Asclepius基准以评估医疗多模态大语言模型的能力 large language model
6 Puzzle Solving using Reasoning of Large Language Models: A Survey 通过大型语言模型推理解决难题的调查研究 large language model
7 Can Large Language Models perform Relation-based Argument Mining? 利用大型语言模型提升基于关系的论证挖掘性能 large language model
8 I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses 提出利用LLM生成响应进行大语言模型微调以提升推理性能 large language model
9 KnowTuning: Knowledge-aware Fine-tuning for Large Language Models 提出KnowTuning以解决大语言模型知识利用不足问题 large language model
10 OneBit: Towards Extremely Low-bit Large Language Models 提出OneBit框架以实现极低位宽的大型语言模型量化 large language model
11 Can Large Multimodal Models Uncover Deep Semantics Behind Images? 提出DEEPEVAL基准以评估多模态模型的深层语义理解能力 multimodal
12 Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs 提出基于动态属性图的受控文本生成框架以提升文本属性控制能力 large language model
13 MMMModal -- Multi-Images Multi-Audio Multi-turn Multi-Modal 提出MMMModal以解决多模态理解挑战 large language model multimodal ✅
14 Language Models Don't Learn the Physical Manifestation of Language 提出H-Test以揭示语言模型的感知缺陷 chain-of-thought
15 Dissecting Human and LLM Preferences 剖析人类与大型语言模型偏好以提升模型对齐性 large language model ✅
16 MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning 提出MoRAL以解决大语言模型的终身学习问题 large language model
17 ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection 提出ToBlend以解决AI内容检测模型的鲁棒性问题 large language model
18 SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization 提出SEE框架以优化大语言模型的提示设计 large language model
19 EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries 提出事件驱动的知识编辑方法以解决知识更新中的不确定性问题 large language model
20 C-ICL: Contrastive In-context Learning for Information Extraction 提出C-ICL以提升信息提取任务的学习效果 large language model
21 LLM can Achieve Self-Regulation via Hyperparameter Aware Generation 提出超参数感知生成方法以实现LLM自我调节 large language model
22 Disclosure and Mitigation of Gender Bias in LLMs 提出间接探测框架以揭示和缓解大型语言模型中的性别偏见 large language model
23 M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection 提出M4GT-Bench以解决机器生成文本检测问题 large language model ✅
24 KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph 提出KG-Agent框架以提升知识图谱推理能力 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
25 Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models 提出多视角一致性方法以提升大语言模型的置信度估计 MPC 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🔗⭐
26 LaCo: Large Language Model Pruning via Layer Collapse 提出LaCo以解决大语言模型剪枝问题 distillation large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页