cs.CL（2025-01-14）

📊 共 26 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following InstructCell：基于多模态AI Copilot的单细胞分析指令跟随框架 large language model foundation model instruction following
2 MiniMax-01: Scaling Foundation Models with Lightning Attention MiniMax-01系列模型：通过闪电注意力机制扩展基础模型，实现百万级上下文处理。 foundation model
3 Large Language Models For Text Classification: Case Study And Comprehensive Review 对比LLM与传统模型在文本分类任务中的性能，揭示不同提示策略的影响。 large language model
4 OptiChat: Bridging Optimization Models and Practitioners with Large Language Models OptiChat：利用大语言模型连接优化模型与领域专家，实现自然语言交互。 large language model
5 Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models 提出ICR^2基准与检索增强方法，提升长文本大模型在复杂上下文中的检索与推理能力 large language model
6 Dynamic Multimodal Sentiment Analysis: Leveraging Cross-Modal Attention for Enabled Classification 提出基于跨模态注意力机制的多模态情感分析模型，提升情感分类精度。 multimodal
7 A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models 提出多编码器冻结解码器方法，高效微调大型语言模型并提升多任务性能。 large language model
8 PokerBench: Training Large Language Models to become Professional Poker Players PokerBench：训练大型语言模型成为专业扑克玩家的基准测试 large language model
9 Potential and Perils of Large Language Models as Judges of Unstructured Textual Data 研究LLM作为非结构化文本数据评判者的潜力与风险，并与人工评估对比。 large language model
10 Refusal Behavior in Large Language Models: A Nonlinear Perspective 揭示大语言模型拒绝行为的非线性特性，助力更安全的AI部署 large language model
11 Consistency of Responses and Continuations Generated by Large Language Models on Social Media 研究表明，大型语言模型在社交媒体文本生成中倾向于中和负面情绪。 large language model
12 Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT 通过层级分析BERT，探索其在叙事聚类中对内容和风格的表征能力 large language model
13 Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack Tag&Tab：利用关键词的成员推理攻击检测大语言模型预训练数据 large language model
14 CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation CWEval：提出面向LLM代码生成的功能与安全性的结果驱动型评测框架 large language model ✅
15 Efficient Real-time Refinement of Language Model Text Generation 提出Streaming-VR，实现语言模型生成文本的实时高效修正。 large language model
16 HALoGEN: Fantastic LLM Hallucinations and Where to Find Them HALoGEN：构建LLM幻觉基准，揭示并分类生成模型的事实性错误。 large language model
17 TriAdaptLoRA: Brain-Inspired Triangular Adaptive Low-Rank Adaptation for Parameter-Efficient Fine-Tuning TriAdaptLoRA：受脑科学启发的三角自适应低秩适配高效微调大语言模型 large language model
18 Labeling Free-text Data using Language Model Ensembles 提出基于语言模型集成的方法，用于在隐私约束下标注自由文本数据 large language model
19 Exploring Robustness of Multilingual LLMs on Real-World Noisy Data 研究多语言LLM在真实噪声数据上的鲁棒性，发现mT5模型表现更优 large language model
20 Enhancing Automated Interpretability with Output-Centric Feature Descriptions 提出输出中心特征描述方法，提升大语言模型自动可解释性并发现“死亡”特征。 large language model
21 ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving ArithmAttack：评估LLM在数学问题求解中对噪声上下文的鲁棒性 large language model
22 OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training OpenCSG中文语料库：为中文LLM训练提供高质量数据集 large language model
23 Developing Enhanced Conversational Agents for Social Virtual Worlds 提出增强型会话代理方法，应用于社交虚拟世界 Second Life multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
24 ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding ReARTeR：通过可信过程奖励增强RAG系统的推理能力 preference learning large language model chain-of-thought
25 Optimizing Language Models for Grammatical Acceptability: A Comparative Study of Fine-Tuning Techniques 对比微调技术优化语言模型语法可接受性，提升计算效率 distillation large language model

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

#题目一句话要点标签🔗⭐
26 The Theater Stage as Laboratory: Review of Real-Time Comedy LLM Systems for Live Performance 评估实时喜剧LLM系统：剧场舞台作为AI喜剧的实验场所 HuMoR

⬅️ 返回 cs.CL 首页 · 🏠 返回主页