cs.CL（2024-09-26）

📊 共 27 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) (21 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 MIO: A Foundation Model on Multimodal Tokens MIO：基于多模态Token的端到端自回归通用基础模型，支持语音、文本、图像和视频的理解与生成。 large language model foundation model multimodal
2 ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue ZALM3：通过多轮多模态医疗对话中的上下文信息零样本增强视觉-语言对齐 large language model multimodal visual grounding
3 MultiClimate: Multimodal Stance Detection on Climate Change Videos 提出MultiClimate数据集，用于气候变化视频的多模态立场检测研究 large language model multimodal ✅
4 T3: A Novel Zero-shot Transfer Learning Framework Iteratively Training on an Assistant Task for a Target Task 提出T3框架，通过迭代训练辅助任务提升LLM在长文本摘要任务上的零样本迁移能力 large language model zero-shot transfer
5 DualCoTs: Dual Chain-of-Thoughts Prompting for Sentiment Lexicon Expansion of Idioms 提出DualCoTs方法，利用双重思维链提示扩展成语情感词典。 large language model chain-of-thought
6 Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models 提出Logic-of-Thought，通过注入逻辑信息增强大语言模型的复杂推理能力 large language model chain-of-thought
7 RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking 提出RED QUEEN攻击，揭示大型语言模型在隐蔽多轮越狱攻击下的脆弱性 large language model ✅
8 AER-LLM: Ambiguity-aware Emotion Recognition Leveraging Large Language Models AER-LLM：利用大语言模型进行歧义感知的多情感识别 large language model
9 Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review 评估大型语言模型在医学领域摘要任务中的应用及挑战 large language model
10 Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models 提出基于时间适配器的大语言模型，用于从纵向社交媒体数据中提取情感聚合信息。 large language model
11 Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect Atlas-Chat：为低资源摩洛哥阿拉伯方言定制的大语言模型 large language model
12 EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models EMMA-500：增强大规模多语言LLM适应性，提升低资源语言覆盖 large language model
13 Data Proportion Detection for Optimized Data Management for Large Language Models 提出数据比例检测方法，用于优化大语言模型预训练数据管理 large language model
14 Inference-Time Language Model Alignment via Integrated Value Guidance 提出集成价值引导（IVG）方法，在推理时高效对齐语言模型与人类偏好。 large language model instruction following
15 BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search BEATS：利用BackVerify和自适应消歧高效树搜索优化LLM数学能力 large language model
16 Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model 提出基于少量样本提示的Pairwise排序方法，有效提升非参数检索模型性能 large language model
17 Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models 提出文本分类快捷方式学习基准，分析语言模型对复杂快捷方式的依赖性。 large language model ✅
18 A Generalized LLM-Augmented BIM Framework: Application to a Speech-to-BIM system 提出LLM增强的通用BIM框架，加速自然语言交互式BIM应用开发 large language model
19 Zero- and Few-shot Named Entity Recognition and Text Expansion in Medication Prescriptions using ChatGPT 利用ChatGPT在药物处方中实现零样本和少样本命名实体识别与文本扩展 large language model
20 Evaluating Multilingual Long-Context Models for Retrieval and Reasoning mLongRR数据集揭示多语言长文本模型在检索和推理上的性能差距 large language model
21 PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification 提出PEDRO以解决大语言模型的高效微调问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
22 Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness 提出自监督偏好优化SPO，提升语言模型对偏好程度的理解能力 reinforcement learning RLHF DPO ✅
23 Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization 提出DQO：利用翻译质量估计模型优化神经机器翻译，实现跨语种人类偏好对齐 reinforcement learning RLHF DPO
24 Reducing and Exploiting Data Augmentation Noise through Meta Reweighting Contrastive Learning for Text Classification 提出基于元重加权对比学习的文本分类方法，降低并利用数据增强噪声。 contrastive learning
25 Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment 揭示奖励模型质量对LLM对齐的影响：提出CHH-RLHF并系统评估奖励模型。 RLHF large language model
26 Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards 提出基于强化学习的评分感知多重奖励自回归多特质作文评分模型 reinforcement learning
27 Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult 提出MIPO，通过调节干预度优化偏好，提升模型对齐效果。 RLHF DPO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页