cs.CL（2024-05-09）

📊 共 22 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) (21 🔗2) 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 Hypothesis Testing Prompting Improves Deductive Reasoning in Large Language Models 提出假设检验提示方法，提升大语言模型在演绎推理任务中的性能 large language model chain-of-thought
2 LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought 提出PedCoT，利用教学式思维链提升LLM数学推理错误识别能力 large language model chain-of-thought
3 Enhancing Creativity in Large Language Models through Associative Thinking Strategies 通过联想思维策略提升大型语言模型的创造力 large language model
4 Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models 提出通用声学对抗攻击，使Whisper语音模型忽略语音内容 foundation model
5 Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding? 质疑PPL作为长文本理解评估指标的有效性，揭示其局限性 large language model
6 Digital Diagnostics: The Potential Of Large Language Models In Recognizing Symptoms Of Common Illnesses 评估大型语言模型在常见疾病症状识别中的潜力，为数字诊断提供新思路 large language model
7 Towards a More Inclusive AI: Progress and Perspectives in Large Language Model Training for the Sámi Language 针对萨米语，探索低资源场景下大语言模型训练的包容性AI方法 large language model
8 Can large language models understand uncommon meanings of common words? 构建LeSC数据集，揭示大语言模型在理解常见词语非常见含义方面的不足 large language model
9 Exploring the Capabilities of Large Multimodal Models on Dense Text 提出DT-VQA数据集，探索大型多模态模型在密集文本理解任务中的能力。 multimodal ✅
10 Can We Use Large Language Models to Fill Relevance Judgment Holes? 利用大型语言模型填补相关性判断缺失，扩展测试集以提升检索系统评估的可靠性。 large language model
11 Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis 提出基于大语言模型和持续学习的LLM-CL模型，解决面向方面情感分析中的领域知识迁移和遗忘问题。 large language model
12 Unveiling the Competitive Dynamics: A Comparative Evaluation of American and Chinese LLMs 对比中美大语言模型，揭示语言和任务差异下的性能差距 large language model multimodal
13 Natural Language Processing RELIES on Linguistics 强调语言学在自然语言处理中的持久重要性，应对大语言模型带来的挑战。 large language model
14 Towards a Path Dependent Account of Category Fluency 提出路径依赖的类别流畅性模型，解决认知机制的争议 large language model
15 OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning OpenBA-V2：通过快速多阶段剪枝实现77.3%高压缩率 large language model
16 Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning Smurfs：基于上下文高效DFSDT的多智能体工具规划系统 large language model
17 Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? 研究表明：在LLM微调中引入新知识会增加幻觉现象 large language model
18 Experimental Pragmatics with Machines: Testing LLM Predictions for the Inferences of Plain and Embedded Disjunctions 利用大型语言模型预测析取推理，验证其在实验语用学中的应用潜力 large language model
19 Exploring the Human-LLM Synergy in Advancing Theory-driven Qualitative Analysis 提出CHALET，利用人-LLM协同推进理论驱动的定性分析，发现新见解。 large language model
20 Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM 提出CoA：一种语义驱动的上下文多轮攻击方法，用于评估LLM的安全性。 large language model
21 OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs OpenFactCheck：构建、评估定制化事实核查系统，评估声明和LLM的事实性 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🔗⭐
22 From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences 构建Cline数据集并微调MLLM，用于预测英印混合语语句的可接受性。 predictive model large language model zero-shot transfer

⬅️ 返回 cs.CL 首页 · 🏠 返回主页