cs.CL（2024-07-19）

📊 共 19 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context 提出情境化对抗提示攻击，提升大语言模型攻击的人类可理解性与隐蔽性 large language model chain-of-thought
2 Multimodal Misinformation Detection using Large Vision-Language Models 提出基于大型视觉-语言模型的多模态错误信息检测方法，提升证据检索和事实核查性能。 large language model multimodal
3 HeCiX: Integrating Knowledge Graphs and Large Language Models for Biomedical Research 提出HeCiX，融合知识图谱与大语言模型，助力生物医学研究。 large language model
4 CVE-LLM : Automatic vulnerability evaluation in medical device industry using large language models 提出CVE-LLM，利用大语言模型自动评估医疗设备漏洞。 large language model
5 Adversarial Databases Improve Success in Retrieval-based Large Language Models 对抗性数据库提升了基于检索的大语言模型在医学问答中的成功率 large language model
6 Internal Consistency and Self-Feedback in Large Language Models: A Survey 提出自反馈框架，从内部一致性视角统一分析和提升大语言模型推理能力。 large language model ✅
7 Evaluating the Reliability of Self-Explanations in Large Language Models 评估大语言模型自解释的可靠性，提出反事实解释方法 large language model
8 Unipa-GPT: Large Language Models for university-oriented QA in Italian Unipa-GPT：基于大型语言模型的意大利语大学问答系统 large language model
9 ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities ChatQA 2：基于Llama 3.0，提升长文本理解和RAG能力，媲美GPT-4-Turbo instruction following
10 Open Artificial Knowledge 提出Open Artificial Knowledge (OAK)数据集，解决LLM训练数据稀缺问题 large language model
11 Check-Eval: A Checklist-based Approach for Evaluating Text Quality 提出Check-Eval以解决文本生成质量评估问题 large language model
12 LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains 评估GPT-4对新闻网站政治倾向的标注能力，揭示其局限与潜在偏见。 large language model
13 LeKUBE: A Legal Knowledge Update BEnchmark LeKUBE：一个用于评估法律领域大语言模型知识更新的基准 large language model
14 SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy SQLfuse：通过全面LLM协同增强Text-to-SQL性能 large language model
15 ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness? ECCO：在保证功能正确性的前提下，提升模型生成代码的效率 large language model
16 Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis 提出一种基于LLM的新闻主题自动分类框架，用于分析法国广播新闻中的性别偏见。 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🔗⭐
17 Compact Language Models via Pruning and Knowledge Distillation 通过剪枝与知识蒸馏构建紧凑型语言模型，降低训练成本并提升性能。 distillation large language model
18 Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization 提出基于直接偏好优化的Encoder-Decoder模型，显著提升临床文本阅读理解效果。 DPO direct preference optimization
19 Improving Retrieval in Sponsored Search by Leveraging Query Context Signals 利用查询上下文信号，改进赞助搜索中的检索效果 curriculum learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页