cs.CL（2024-08-20）

📊 共 30 篇论文 | 🔗 10 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗10) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications 提出Open-FinLLMs，首个开源多模态金融大语言模型，提升金融任务性能。 large language model multimodal
2 Benchmarking Large Language Models for Math Reasoning Tasks 数学推理任务LLM基准测试：比较不同模型和上下文学习算法 large language model foundation model
3 Beyond Labels: Aligning Large Language Models with Human-like Reasoning 提出DFAR数据集和L+R微调方法，提升LLM伦理推理能力 large language model ✅
4 Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models 提出对抗性框架，评估并提升大语言模型知识遗忘的鲁棒性 large language model
5 GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models GS-KGC：基于生成式子图的知识图谱补全框架，利用大语言模型进行推理。 large language model
6 Towards Efficient Large Language Models for Scientific Text: A Review 针对科学文本的高效大型语言模型研究综述：模型小型化与数据质量提升 large language model
7 MEGen: Generative Backdoor into Large Language Models via Model Editing 提出MEGen：一种基于模型编辑的大语言模型生成式后门攻击方法 large language model ✅
8 Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory 提出基于贝叶斯理论的BTBR框架，用于识别和缓解大语言模型中的隐式偏见。 large language model
9 CTP-LLM: Clinical Trial Phase Transition Prediction Using Large Language Models CTP-LLM：利用大型语言模型预测临床试验阶段转换 large language model
10 SysBench: Can Large Language Models Follow System Messages? 提出SysBench以评估大语言模型对系统消息的遵循能力 large language model ✅
11 Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model Otter：通过非侵入式参数插入，高效预测奖励以干预大语言模型推理 large language model ✅
12 CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding? 提出CodeJudge-Eval以评估大型语言模型的代码理解能力 large language model ✅
13 Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models 提出基于注意力机制的LLM不确定性量化方法，提升生成结果可靠性。 large language model
14 Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information 提出ATF方法，提升大语言模型在含无关信息问题中的鲁棒性 large language model
15 An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs 提出SpaMo框架，利用空间构型与运动动态信息，提升基于LLM的手语翻译效率 large language model
16 Emotional RAG LLMs: Reading Comprehension for the Open Internet 提出情感RAG LLM，提升大语言模型在开放互联网文本上的阅读理解能力 large language model
17 LBC: Language-Based-Classifier for Out-Of-Variable Generalization 提出基于语言的分类器LBC，解决表格数据中变量泛化难题。 large language model ✅
18 Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in? 揭示多语言LLM内部表征：探究模型在何种语言中“思考” large language model
19 Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups 提出融合对话流与风格的数据增强方法，提升口语对话系统在低资源用户群体上的表现。 large language model
20 Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data 提出基于美国劳工数据的LLM职业偏见校正方法，提升模型公平性 large language model
21 Public Health in Disaster: Emotional Health and Life Incidents Extraction during Hurricane Harvey 提出结合BERT、LDA、GNN和LLM的情绪与事件提取框架，用于灾害公共健康分析。 large language model
22 Security Attacks on LLM-based Code Completion Tools 针对LLM代码补全工具的安全攻击与数据泄露研究 large language model ✅
23 CHECKWHY: Causal Fact Verification via Argument Structure 提出CheckWhy数据集，用于因果关系事实核查，强调论证结构的重要性。 chain-of-thought
24 BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model 提出BEYOND DIALOGUE框架，解决角色扮演语言模型中对话与角色设定不一致问题 large language model ✅
25 Crafting Tomorrow's Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian 构建多语种神经新闻生成与检测基准数据集，应对LLM时代虚假信息挑战 large language model
26 REInstruct: Building Instruction Data from Unlabeled Corpus REInstruct：一种从无标签语料库自动构建指令数据的可扩展方法 large language model ✅
27 Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution 综述表格数据语言建模：回顾基础、技术与演进 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🔗⭐
28 Athena: Safe Autonomous Agents with Verbal Contrastive Learning 提出Athena框架，利用对比学习提升LLM自主Agent的安全性。 contrastive learning large language model
29 Mistral-SPLADE: LLMs for better Learned Sparse Retrieval Mistral-SPLADE：利用LLM改进学习型稀疏检索，显著提升检索性能 distillation large language model
30 Speech Representation Learning Revisited: The Necessity of Separate Learnable Parameters and Robust Data Augmentation 提出O-HuBERT模型，通过分离参数学习和增强数据增强提升语音表征学习效果 representation learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页