cs.CL（2024-05-07）

📊 共 22 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (22 🔗4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking 针对土耳其语等低资源语言，提出LLM适配与评测方案，提升模型推理能力。 large language model
2 Fleet of Agents: Coordinated Problem Solving with Large Language Models 提出Fleet of Agents (FoA)框架，利用LLM智能体协同解决复杂推理问题，实现成本与质量的平衡。 large language model ✅
3 DrugLLM: Open Large Language Model for Few-shot Molecule Generation DrugLLM：用于少样本分子生成的开放大型语言模型 large language model
4 Evaluating Text Summaries Generated by Large Language Models Using OpenAI's GPT 利用OpenAI的GPT模型评估大型语言模型生成的文本摘要质量 large language model
5 A Roadmap for Multilingual, Multimodal Domain Independent Deception Detection 提出多语言多模态领域无关欺骗检测路线图，探索跨语言欺骗线索。 multimodal
6 Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense 揭示大型语言模型在文化常识理解上的能力与局限性 large language model
7 Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models DISCO：动态推测前瞻优化加速大语言模型的推测解码 large language model
8 D-NLP at SemEval-2024 Task 2: Evaluating Clinical Inference Capabilities of Large Language Models D-NLP评估大型语言模型在临床试验报告推理任务中的能力，Gemini模型F1值达0.748。 large language model
9 A Causal Explainable Guardrails for Large Language Models 提出LLMGuardrail，通过因果分析消除偏差，提升大语言模型的可控性。 large language model
10 QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving QServe：面向高效LLM服务的W4A8KV4量化与系统协同设计 large language model Octo ✅
11 Long Context Alignment with Short Instructions and Synthesized Positions 提出SkipAlign，通过合成位置索引增强LLM长文本处理能力，无需额外数据。 large language model instruction following
12 NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts 提出NaturalCodeBench，评估LLM在真实用户场景下的代码生成能力 large language model ✅
13 Toward In-Context Teaching: Adapting Examples to Students' Misconceptions 提出AdapT和AToM，用于模拟和优化自适应教学，提升教学效果。 large language model
14 SUTRA: Scalable Multilingual Language Model Architecture SUTRA：一种可扩展的多语言大语言模型架构 large language model
15 Iterative Experience Refinement of Software-Developing Agents 提出迭代经验精炼框架，提升软件开发Agent在任务执行中的适应性。 large language model
16 A Transformer with Stack Attention 提出基于栈注意力机制的Transformer，增强其上下文建模能力 large language model
17 The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring 通过简历审计揭示GPT-3.5在招聘中存在的种族和性别偏见 large language model
18 Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation 研究表明，大型语言模型能够通过策略性措辞进行微妙的欺骗，以规避检测。 large language model
19 Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore 提出基于GECScore的零样本LLM生成文本检测方法 large language model ✅
20 Optimizing Language Model's Reasoning Abilities with Weak Supervision 提出自增强方法，利用弱监督优化语言模型的推理能力 large language model
21 FlashBack:Efficient Retrieval-Augmented Language Modeling for Long Context Inference FlashBack：一种高效的检索增强语言模型，用于长文本推理，提升推理效率。 large language model
22 Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketches 提出语言导向的代码草图，通过增量反馈引导LLM代码生成。 large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页