cs.CL（2024-09-20）

📊 共 40 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (35 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (35 篇)

#题目一句话要点标签🔗⭐
1 Utility of Multimodal Large Language Models in Analyzing Chest X-ray with Incomplete Contextual Information 多模态大语言模型提升不完整胸部X光报告解读的准确性 large language model multimodal
2 EMMeTT: Efficient Multimodal Machine Translation Training EMMeTT：高效的多模态机器翻译训练框架，提升语音和文本翻译性能。 foundation model multimodal
3 Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning 提出基于计算机视觉损失函数的LLM微调方法，提升数学问题和问答任务性能。 large language model
4 Unlocking Memorization in Large Language Models with Dynamic Soft Prompting 提出动态软提示方法，提升大型语言模型记忆内容提取的准确性。 large language model
5 The Impact of Large Language Models in Academia: from Writing to Speaking 大规模分析揭示LLM对学术写作和口语表达的潜在影响 large language model
6 Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models 提出AltPO方法，结合正负反馈优化LLM的事实知识遗忘，提升模型效用。 large language model ✅
7 Exploring Scaling Laws for Local SGD in Large Language Model Training 探索局部SGD在大语言模型训练中的扩展规律，适用于松散连接设备。 large language model
8 Diabetica: Adapting Large Language Model to Enhance Multiple Medical Tasks in Diabetes Care and Management Diabetica：针对糖尿病管理的多任务LLM，提升个性化医疗与临床效率 large language model ✅
9 MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models MirrorStories：利用大型语言模型生成个性化叙事，反映多元化身份认同 large language model
10 Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology 利用领域检索增强生成提升医学大语言模型：眼科长文本问答案例研究 large language model
11 LLM for Everyone: Representing the Underrepresented in Large Language Models 针对低资源语言，提出数据与计算高效的LLM泛化与文化对齐方法 large language model
12 STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions 提出STOP数据集，用于评估大型语言模型在冒犯性递进场景中的敏感性。 large language model
13 Measuring Copyright Risks of Large Language Model via Partial Information Probing 通过局部信息探测评估大型语言模型潜在的版权侵权风险 large language model
14 ShizishanGPT: An Agricultural Large Language Model Integrating Tools and Resources ShizishanGPT：集成工具与资源的农业领域大语言模型 large language model ✅
15 EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models EmotionQueen：一个用于评估大型语言模型共情能力的基准 large language model
16 Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time 提出TimeShift基准测试，评估大语言模型在时间维度上的事实回忆能力。 large language model
17 Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia 利用大型语言模型辅助贫血的鉴别诊断，探索临床路径 large language model
18 A Multiple-Fill-in-the-Blank Exam Approach for Enhancing Zero-Resource Hallucination Detection in Large Language Models 提出多重填空题方法，增强大语言模型零资源幻觉检测能力 large language model
19 Transfer Learning with Clinical Concept Embeddings from Large Language Models 利用大型语言模型临床概念嵌入进行迁移学习，提升跨医疗机构知识共享。 large language model
20 Constrained Reasoning Chains for Enhancing Theory-of-Mind in Large Language Models 提出CCoToM以解决大型语言模型的心智理论能力不足问题 large language model
21 A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering 提出一种ASR-free的多模态稠密检索方法，用于语音开放域问答。 multimodal
22 Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey 综述论文：检索增强生成中上下文压缩技术，提升大语言模型性能 large language model
23 JMedBench: A Benchmark for Evaluating Japanese Biomedical Large Language Models JMedBench：用于评估日语生物医学大型语言模型的基准测试 large language model ✅
24 Large Language Model Should Understand Pinyin for Chinese ASR Error Correction 提出拼音增强的GEC模型，提升中文语音识别纠错能力 large language model
25 CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance CITI：提升大语言模型工具利用能力，同时避免牺牲通用性能 large language model
26 CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency 提出CSCE框架，通过因果显著性和一致性增强提升LLM推理能力 large language model chain-of-thought
27 A Multi-LLM Debiasing Framework 提出多LLM去偏框架，显著降低大型语言模型中的偏见 large language model
28 Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino 提出Kalahi：一个手工构建的菲律宾文化LLM评估套件 large language model
29 'Since Lawyers are Males..': Examining Implicit Gender Bias in Hindi Language Generation by LLMs 揭示LLM在印地语生成中显著的性别偏见，远超英语，强调跨语言偏见差异。 large language model
30 Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM Mufu：利用LLM的多语言融合学习提升低资源翻译性能 large language model
31 "I Never Said That": A dataset, taxonomy and baselines on response clarity classification 提出一种基于政治访谈的回答清晰度分类数据集与基线方法，解决公共演讲中含糊不清的问题。 large language model
32 Contextualized Data-Wrangling Code Generation in Computational Notebooks 提出CoCoMine和CoCoNote，用于计算笔记本中上下文感知的数据整理代码生成。 large language model
33 Applying Pre-trained Multilingual BERT in Embeddings for Improved Malicious Prompt Injection Attacks Detection 利用多语言BERT嵌入改进恶意提示注入攻击检测 large language model
34 Towards LifeSpan Cognitive Systems 提出面向终身认知系统的LLM框架，解决经验抽象与长期记忆难题 large language model
35 CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information 提出CFSP：一种高效的LLM结构化剪枝框架，利用粗细粒度激活信息。 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
36 Recent Advancement of Emotion Cognition in Large Language Models 综述大型语言模型在情感认知方面的最新进展，着重分析情感分类、情感生成和心理理论评估。 contrastive learning large language model
37 Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks 提出神经-符号协同蒸馏NesyCD，提升小模型在复杂推理任务上的能力 distillation large language model ✅
38 $\textit{SKIntern}$: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models 提出SKIntern以解决小型语言模型的推理能力不足问题 curriculum learning distillation large language model ✅
39 RRM: Robust Reward Model Training Mitigates Reward Hacking 提出RRM以解决奖励模型训练中的奖励攻击问题，提升LLM对齐效果 DPO large language model
40 Aligning Language Models Using Follow-up Likelihood as Reward Signal 提出基于后续话语似然性的奖励模型FLR，用于对齐语言模型，无需人工或商业LLM标注。 DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页