cs.CL（2024-10-19）

📊 共 14 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) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction Generation SemiHVision：通过半人工标注数据集和微调指令生成增强医学多模态模型 large language model multimodal
2 Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models 提出COFT方法，通过粗到精的关键信息高亮，减少大语言模型中的知识幻觉 large language model
3 On the Diversity of Synthetic Data and its Impact on Training Large Language Models 提出LLM cluster-agent度量合成数据多样性，并验证其对大语言模型训练的影响 large language model
4 Evaluation Of P300 Speller Performance Using Large Language Models Along With Cross-Subject Training 利用大型语言模型和跨主体训练提升P300拼写器性能 large language model
5 Evaluating Deep Unlearning in Large Language Models 提出深度卸载学习框架，评估LLM在删除目标事实及其逻辑推导结果上的能力。 large language model
6 mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation mHumanEval：一个用于评估大语言模型代码生成能力的多语言基准 large language model
7 Are LLMs Good Zero-Shot Fallacy Classifiers? 利用大型语言模型实现零样本谬误分类，提升谬误检测能力。 large language model chain-of-thought ✅
8 An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making 提出GEDI，通过引入选举机制提升LLM多智能体集体决策的多样性和鲁棒性 large language model
9 TrendFact: A Benchmark for Explainable Hotspot Perception in Fact-Checking with Natural Language Explanation 提出TrendFact基准，用于评估可解释的热点感知事实核查能力，并提出FactISR框架提升大语言模型性能。 large language model
10 Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding 通过偏差-多样性分解，解释了最小贝叶斯风险解码的推理缩放定律 large language model ✅
11 CAP: Data Contamination Detection via Consistency Amplification 提出CAP框架，通过一致性放大检测LLM数据污染问题 large language model

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

#题目一句话要点标签🔗⭐
12 Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention 提出基于自蒸馏和统一模态交叉注意力的多模态情感分析方法，有效处理缺失模态问题。 MAE distillation multimodal ✅
13 DM-Codec: Distilling Multimodal Representations for Speech Tokenization DM-Codec通过多模态表示蒸馏进行语音Token化，显著降低了语音转录的错误率。 distillation multimodal ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 Transit Pulse: Utilizing Social Media as a Source for Customer Feedback and Information Extraction with Large Language Model 提出Transit Pulse以解决公共交通社交媒体信息提取问题 PULSE large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页