cs.CL（2025-01-07）

📊 共 20 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4)

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

#题目一句话要点标签🔗⭐
1 LlaMADRS: Prompting Large Language Models for Interview-Based Depression Assessment LlaMADRS：利用大语言模型进行访谈式抑郁症评估 large language model multimodal
2 Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models 首次将阿拉伯语融入机器人视觉语言导航，评估了多种语言模型在导航任务中的性能。 VLN large language model instruction following
3 Agreeing to Interact in Human-Robot Interaction using Large Language Models and Vision Language Models 利用LLM和VLM解决人机交互起始阶段的交互意图判断问题 large language model
4 Multimodal Multihop Source Retrieval for Web Question Answering 提出图推理网络以解决多模态多跳问答问题 multimodal
5 "Yeah Right!" -- Do LLMs Exhibit Multimodal Feature Transfer? 研究表明，语音+文本LLM在隐蔽欺骗检测中优于单模态LLM，体现多模态特征迁移能力。 multimodal
6 Progressive Document-level Text Simplification via Large Language Models 提出ProgDS，通过多阶段LLM协作实现文档级文本简化，显著优于现有方法。 large language model
7 A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models 提出基于序列优化学习的自动化Prompt工程框架，高效搜索Prompt特征。 large language model
8 Reading with Intent -- Neutralizing Intent 提出“意图阅读”任务，通过情感翻译模型中和语境情感，提升RAG系统性能。 large language model
9 Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation 提出REST-PG框架，通过推理增强的自训练提升长文本个性化生成效果 large language model
10 Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection 提出Perplexity Attention Weighted Network (PAWN)用于提升AI生成文本的检测性能。 large language model
11 Can LLMs Ask Good Questions? 评估大型语言模型生成问题的质量，揭示其与人类提问的差异 large language model
12 MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems MTRAG：用于评估检索增强生成系统的多轮对话基准 large language model ✅
13 Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles 提出Calib-n框架，利用LLM响应一致性和优化损失函数提升校准性能，增强LLM可靠性。 large language model
14 Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study 利用辅助任务改进方言槽位和意图检测：以巴伐利亚方言为例 zero-shot transfer
15 Women, Infamous, and Exotic Beings: A Comparative Study of Honorific Usages in Wikipedia and LLMs for Bengali and Hindi 研究维基百科和LLM中对孟加拉语和印地语尊称使用的差异，揭示社会文化偏见。 large language model ✅
16 ISSR: Iterative Selection with Self-Review for Vocabulary Test Distractor Generation 提出ISSR框架，利用自审机制提升词汇测试干扰项生成质量 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
17 Modality-Invariant Bidirectional Temporal Representation Distillation Network for Missing Multimodal Sentiment Analysis 提出MITR-DNet，通过模态不变蒸馏解决缺失多模态情感分析中的异构性与鲁棒性问题。 representation learning distillation multimodal
18 AlphaPO: Reward Shape Matters for LLM Alignment AlphaPO：通过调整奖励函数形状优化LLM对齐，提升指令遵循能力。 reinforcement learning RLHF DPO
19 SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment 提出SLAM：通过选择性语言对齐实现高效的多语言推理 representation learning large language model
20 A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving 提出一种多样性增强的知识蒸馏模型，用于解决实际数学应用题。 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页