cs.CL（2024-12-04）

📊 共 23 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 🔗4) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

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

#题目一句话要点标签🔗⭐
1 Prompting Large Language Models for Clinical Temporal Relation Extraction 利用Prompting技术提升大型语言模型在临床时间关系抽取任务中的性能 large language model
2 A Review on Scientific Knowledge Extraction using Large Language Models in Biomedical Sciences 综述：利用大型语言模型在生物医学领域进行科学知识抽取 large language model
3 Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning 提出Possibility Exploration Fine-Tuning (PEFT)以提升大语言模型输出的语言多样性。 large language model ✅
4 Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media 提出FineRob数据集和OM-CoT方法，提升LLM在社交媒体用户行为模拟的细粒度能力 large language model ✅
5 Acquired TASTE: Multimodal Stance Detection with Textual and Structural Embeddings 提出TASTE：融合文本和结构化嵌入的多模态立场检测方法 multimodal
6 From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents 利用大语言模型驱动的智能体进行社会模拟研究综述，涵盖个体、场景和社会三个层面。 large language model ✅
7 Multimodal Sentiment Analysis Based on BERT and ResNet 提出基于BERT和ResNet的多模态情感分析框架，提升文本图像融合效果 multimodal
8 RedStone: Curating General, Code, Math, and QA Data for Large Language Models RedStone：利用Common Crawl为大语言模型构建通用、代码、数学和问答数据集 large language model
9 ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction 提出 ASR-EC 基准数据集，评估大语言模型在中文语音识别纠错中的性能 large language model
10 Human Variability vs. Machine Consistency: A Linguistic Analysis of Texts Generated by Humans and Large Language Models 通过语言特征分析，揭示人类文本与大语言模型生成文本的差异性。 large language model
11 Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models 提出SoulSpeak，融合隐私保护、双重记忆和领域知识的大语言模型心理治疗聊天机器人。 large language model
12 Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models 研究表明预训练LLM的性别偏见在Prompting后依然存在且高度相关 large language model
13 Intent-driven In-context Learning for Few-shot Dialogue State Tracking 提出IDIC-DST，通过意图驱动的上下文学习解决少样本对话状态跟踪问题 large language model
14 Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts? 揭示安全对齐的LLM在语义相关自然提示下的脆弱性，提出ReG-QA方法。 large language model
15 U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs 提出U-MATH：一个用于评估LLM数学能力的大学水平基准 multimodal
16 AntLM: Bridging Causal and Masked Language Models AntLM：融合因果语言模型与掩码语言模型，提升预训练性能 foundation model
17 Linq-Embed-Mistral Technical Report Linq-Embed-Mistral通过数据精炼显著提升文本检索性能 large language model ✅
18 TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM 提出情感知识工具调用框架，增强LLM在共情回复生成中的能力 large language model
19 REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization REVOLVE：通过追踪文本优化中响应演变来优化AI系统 large language model
20 CBEval: A framework for evaluating and interpreting cognitive biases in LLMs CBEval：一个用于评估和解释LLM中认知偏差的框架 large language model
21 Curriculum-style Data Augmentation for LLM-based Metaphor Detection 提出课程学习风格数据增强方法，用于微调LLM以提升隐喻检测性能。 large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
22 Byte BPE Tokenization as an Inverse string Homomorphism 揭示Tokenization本质：作为字符串同态逆映射，不影响LLM对上下文无关语言的识别能力 OMOMO large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
23 Alignment at Pre-training! Towards Native Alignment for Arabic LLMs 面向阿拉伯语LLM的原生对齐：在预训练阶段实现模型对齐 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页