cs.CL（2024-02-23）

📊 共 32 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) (26 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 On the Multi-turn Instruction Following for Conversational Web Agents 提出自反记忆增强规划以解决多轮指令跟随问题 large language model instruction following
2 A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models 提出数据中心方法生成真实高质量患者总结 large language model
3 ArabianGPT: Native Arabic GPT-based Large Language Model 提出ArabianGPT以解决阿拉伯语大语言模型不足问题 large language model
4 Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models 提出基于检索增强生成的LLM方法以解决因果图发现问题 large language model
5 Machine Unlearning of Pre-trained Large Language Models 提出机器遗忘方法以解决大语言模型的隐私问题 large language model
6 Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations 提出自对齐方法以提升大语言模型对未知问题的响应能力 large language model
7 Fine-tuning Large Language Models for Domain-specific Machine Translation 提出DragFT框架以解决领域特定机器翻译问题 large language model
8 KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models 提出KIEval框架以解决大语言模型评估中的数据污染问题 large language model
9 Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models 提出Interactive-KBQA以解决知识库问答中的复杂问题解析 large language model
10 Executing Natural Language-Described Algorithms with Large Language Models: An Investigation 利用大型语言模型执行自然语言描述的算法 large language model
11 ToMBench: Benchmarking Theory of Mind in Large Language Models 提出ToMBench以解决大语言模型的心智理论评估问题 large language model
12 CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models 提出CloChat以解决个性化对话代理的互动问题 large language model
13 Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models 提出实例级前缀的细粒度去毒化方法以解决大语言模型的毒性问题 large language model
14 NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data 提出NuNER以解决命名实体识别任务的高效数据利用问题 large language model foundation model
15 Language-Based User Profiles for Recommendation 提出语言基础用户画像以解决推荐系统冷启动问题 large language model
16 LLMs as Meta-Reviewers' Assistants: A Case Study 利用大型语言模型辅助元评审者提升评审效率 large language model
17 Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes 提出脑启发的双阶段方法以增强数学推理能力 large language model ✅
18 An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning 提出数据能力边界策略以优化LLMs数学推理能力 large language model ✅
19 Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning Strategies 提出基于LLM的实体排名方法以解决概念空间维度问题 large language model
20 Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples 通过自动生成训练数据提升句子嵌入效果 large language model
21 AttributionBench: How Hard is Automatic Attribution Evaluation? 提出AttributionBench以解决自动归因评估难题 large language model
22 Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions 提出一种方法研究Transformer中注意力与MLP的交互 large language model
23 Fine-Grained Self-Endorsement Improves Factuality and Reasoning 提出自我认可框架以改善语言模型的事实性和推理能力 large language model
24 API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs 提出API-BLEND以解决API任务数据不足问题 large language model
25 DEEM: Dynamic Experienced Expert Modeling for Stance Detection 提出动态经验专家建模以解决立场检测问题 large language model
26 ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval 提出ColBERT-XM以解决多语言信息检索中的数据稀缺问题 zero-shot transfer

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

#题目一句话要点标签🔗⭐
27 Unlocking the Power of Large Language Models for Entity Alignment 提出ChatEA以解决知识图谱实体对齐问题 representation learning large language model
28 Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency 提出偏差-波动框架以评估大型语言模型的刻板印象问题 reinforcement learning large language model
29 Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization 提出利用领域知识的高效奖励建模方法以解决RLHF中的标注挑战 reinforcement learning RLHF
30 Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings 提出自适应重构对比学习框架以解决无监督句子嵌入问题 contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
31 Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models 利用大型语言模型生成幽默数据集以解决幽默检测问题 HuMoR large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
32 How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries 提出TechHazardQA以揭示LLMs在指令响应中的伦理脆弱性 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页