cs.CL（2024-06-07）

📊 共 33 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (28 🔗8) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (28 篇)

#题目一句话要点标签🔗⭐
1 An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models 研究多模态大语言模型参数高效微调方法，适配器表现最佳。 large language model multimodal ✅
2 What do MLLMs hear? Examining reasoning with text and sound components in Multimodal Large Language Models 研究音频多模态大语言模型推理能力，揭示其文本推理在音频分类中的局限性 large language model multimodal
3 AICoderEval: Improving AI Domain Code Generation of Large Language Models AICoderEval：提升大语言模型在AI领域代码生成能力的数据集与框架 large language model multimodal ✅
4 FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models 提出FedLLM-Bench，为联邦学习大语言模型提供真实基准测试平台 large language model ✅
5 Transforming Dental Diagnostics with Artificial Intelligence: Advanced Integration of ChatGPT and Large Language Models for Patient Care 利用ChatGPT和大型语言模型革新牙科诊断，提升患者护理水平 large language model
6 SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models 提出SpaRC框架与SpaRP数据集，评估大语言模型在空间推理上的能力。 large language model
7 Revisiting Catastrophic Forgetting in Large Language Model Tuning 研究LLM微调中的灾难性遗忘，提出基于loss landscape平坦化的缓解方法 large language model
8 LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model LawGPT：一个中文法律知识增强的大型语言模型，专为中文法律应用设计。 large language model ✅
9 Are Large Language Models More Empathetic than Humans? 评估大型语言模型同理心：LLM在同理心回应方面超越人类 large language model
10 TCMD: A Traditional Chinese Medicine QA Dataset for Evaluating Large Language Models 构建TCMD：一个用于评估大型语言模型的中医QA数据集 large language model
11 CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models 提出CRiskEval中文风险评估基准数据集，用于评估大型语言模型的潜在风险倾向。 large language model ✅
12 Mixture-of-Agents Enhances Large Language Model Capabilities 提出混合Agent模型(MoA)，提升大语言模型在多项任务上的性能 large language model
13 Large Language Model-guided Document Selection 提出基于大语言模型指导的文档选择方法，提升预训练效率。 large language model
14 Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models 探索少样本学习在低资源跨语言摘要中的应用，提升大语言模型性能 large language model
15 LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs 提出数学主题树基准（MaTT），用于全面评估大型语言模型（LLMs）的数学推理能力。 large language model chain-of-thought
16 Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models 提出一种基于随机森林知识迁移的LLM训练方法，提升数值数据处理能力。 large language model chain-of-thought
17 GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents GameBench：提出用于评估LLM智能体战略推理能力的跨领域基准测试 large language model chain-of-thought
18 BAMO at SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense BAMO团队提出结合微调、CoT和ReConcile的方法，解决SemEval-2024 BRAINTEASER常识推理难题。 large language model chain-of-thought
19 Uncertainty Aware Learning for Language Model Alignment 提出不确定性感知学习UAL，提升LLM在不同任务场景下的对齐效果 large language model foundation model
20 DALD: Improving Logits-based Detector without Logits from Black-box LLMs DALD：无需源LLM logits，对齐分布提升黑盒LLM文本检测 large language model
21 Multi-Head RAG: Solving Multi-Aspect Problems with LLMs 提出Multi-Head RAG，利用多头注意力解决LLM在多方面问题上的检索增强生成。 large language model
22 Scenarios and Approaches for Situated Natural Language Explanations 提出情境化自然语言解释数据集SBE，评估LLM在不同用户场景下的解释能力。 large language model
23 Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs 提出对抗调优框架，增强大型语言模型抵御未知越狱攻击的能力 large language model
24 Quantifying Geospatial in the Common Crawl Corpus 量化Common Crawl语料库中的地理空间信息，为LLM空间推理研究奠定基础 large language model
25 SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals SelfGoal：提升语言Agent在复杂任务中实现高层目标的能力 large language model
26 CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search 提出CHIQ，利用开源LLM增强对话搜索中的查询改写，尤其针对歧义查询。 large language model ✅
27 MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter MEFT：通过稀疏Adapter实现内存高效的大语言模型微调 large language model ✅
28 DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization 提出DiNeR数据集，用于评估组合泛化能力，解决现有数据集的局限性。 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
29 Extroversion or Introversion? Controlling The Personality of Your Large Language Models 提出PISF方法，实现对大型语言模型人格更有效和鲁棒的控制。 reinforcement learning RLHF large language model
30 A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques 深入研究参数高效偏好对齐技术的权衡，为LLM对齐提供指导。 RLHF DPO large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
31 Language Guided Skill Discovery 提出语言引导的技能发现框架LGSD，提升机器人技能的语义多样性 legged robot manipulation large language model
32 Annotating FrameNet via Structure-Conditioned Language Generation 提出一种基于结构条件语言生成的FrameNet标注方法，用于低资源场景下的语义角色标注数据增强。 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
33 Creating an AI Observer: Generative Semantic Workspaces 提出生成式语义工作空间GSW，模拟人类观察者理解文本并预测行为。 semantic map

⬅️ 返回 cs.CL 首页 · 🏠 返回主页