cs.CL（2024-03-02）

📊 共 16 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) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining 提出MuseGraph以解决图挖掘任务中的模型重训练问题 large language model foundation model chain-of-thought
2 Large Language Multimodal Models for 5-Year Chronic Disease Cohort Prediction Using EHR Data 提出多模态大语言模型以提高慢性病预测准确性 large language model multimodal
3 API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access 提出无需Logit访问的保形预测方法以解决LLM不确定性量化问题 large language model
4 Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal 提出自合成复习方法以解决大语言模型的灾难性遗忘问题 large language model
5 IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact 提出IntactKV以解决大语言模型量化性能下降问题 large language model ✅
6 STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models 提出动态主动学习结合LoRA以解决大语言模型数据高效微调问题 large language model
7 LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems 提出LM4OPT以解决自然语言到数学优化问题的转化挑战 large language model
8 LLMCRIT: Teaching Large Language Models to Use Criteria 提出LLMCRIT框架以提升大型语言模型的任务反馈能力 large language model
9 Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers 评估大型语言模型在短篇小说摘要中的表现与作者合作 large language model
10 LAB: Large-Scale Alignment for ChatBots 提出LAB以解决大规模聊天机器人训练中的可扩展性问题 large language model instruction following
11 A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization 提出AI生成文本取证系统以应对信息生态风险 large language model
12 ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies 提出ParallelPARC以生成复杂自然语言类比 large language model
13 DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling 提出DMoERM以解决奖励模型训练中的多任务干扰与噪声问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
14 Improving the Validity of Automatically Generated Feedback via Reinforcement Learning 提出基于强化学习的反馈生成与评估框架以提升有效性 reinforcement learning DPO direct preference optimization
15 Distilling Text Style Transfer With Self-Explanation From LLMs 提出CoTeX框架以解决文本风格迁移问题 distillation large language model chain-of-thought
16 A Survey on Temporal Knowledge Graph: Representation Learning and Applications 综述时序知识图谱表示学习及其应用 representation learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页