cs.CL（2023-10-10）

📊 共 35 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models 提出GeM-CoT以解决混合任务场景中的推理能力不足问题 large language model chain-of-thought
2 TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models 提出TRACE基准以评估大型语言模型的持续学习能力 large language model instruction following
3 Temporally Aligning Long Audio Interviews with Questions: A Case Study in Multimodal Data Integration 提出INDENT框架以解决长音频访谈与问题对齐问题 multimodal
4 GeoLLM: Extracting Geospatial Knowledge from Large Language Models 提出GeoLLM以提升地理空间预测任务的性能 large language model ✅
5 Constructive Large Language Models Alignment with Diverse Feedback 提出构建性多样反馈方法以增强大语言模型对人类价值的对齐 large language model
6 Towards Mitigating Hallucination in Large Language Models via Self-Reflection 提出自我反思方法以缓解大型语言模型的幻觉问题 large language model
7 Get the gist? Using large language models for few-shot decontextualization 提出基于大语言模型的少量样本去上下文化方法 large language model
8 Model Tuning or Prompt Tuning? A Study of Large Language Models for Clinical Concept and Relation Extraction 提出软提示学习算法以提升临床概念与关系提取性能 large language model
9 Making Large Language Models Perform Better in Knowledge Graph Completion 提出知识前缀适配器以提升大语言模型在知识图谱补全中的表现 large language model ✅
10 Multilingual Jailbreak Challenges in Large Language Models 提出自我防御框架以应对大型语言模型的多语言监狱破解挑战 large language model ✅
11 A Semantic Invariant Robust Watermark for Large Language Models 提出语义不变的鲁棒水印方法以解决大语言模型的安全性与攻击性问题 large language model ✅
12 What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models 提出C-VQA数据集以评估多模态语言模型的反事实推理能力 large language model
13 SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network 提出SpikeCLIP以解决多模态脉冲神经网络的特征对齐问题 multimodal ✅
14 Automatic Macro Mining from Interaction Traces at Scale 提出基于大语言模型的宏任务自动提取方法以解决移动交互分析问题 large language model
15 LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression 提出LongLLMLingua以解决长上下文场景中的LLM性能问题 large language model
16 Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency 提出基于语言模型的测试生成方法以提升K-12学生阅读评估效率 large language model
17 Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning 提出Sheared LLaMA以加速语言模型预训练 large language model
18 Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task 提出统一鲁棒性评估框架以解决LLMs在噪声插槽填充任务中的问题 large language model
19 Let Models Speak Ciphers: Multiagent Debate through Embeddings 提出CIPHER以解决LLM间信息传递不足问题 large language model
20 Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding 提出TOOLDEC以解决大型语言模型工具使用中的语法错误问题 large language model
21 Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation 提出生成利用攻击以解决开源LLM的监控失效问题 large language model ✅
22 Rationale-Enhanced Language Models are Better Continual Relation Learners 提出基于理由增强的语言模型以解决持续关系学习问题 large language model
23 Evolution of Natural Language Processing Technology: Not Just Language Processing Towards General Purpose AI 探讨自然语言处理技术演变以推动通用人工智能 large language model
24 LLMs as Potential Brainstorming Partners for Math and Science Problems 探索大型语言模型在数学与科学问题中的头脑风暴潜力 large language model
25 A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection 提出一种新基准和逆验证方法以检测段落级幻觉 large language model
26 Improved prompting and process for writing user personas with LLMs, using qualitative interviews: Capturing behaviour and personality traits of users 提出改进的提示与流程以利用LLM创建用户角色 large language model
27 Selective Demonstrations for Cross-domain Text-to-SQL 提出ODIS框架以解决跨领域文本到SQL的演示选择问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
28 Sparse Fine-tuning for Inference Acceleration of Large Language Models 提出稀疏微调方法以加速大型语言模型推理 distillation large language model
29 Improving Contrastive Learning of Sentence Embeddings with Focal-InfoNCE 提出Focal-InfoNCE以增强句子嵌入的对比学习 contrastive learning
30 A Novel Contrastive Learning Method for Clickbait Detection on RoCliCo: A Romanian Clickbait Corpus of News Articles 提出一种新颖的对比学习方法以解决罗马尼亚点击诱饵检测问题 contrastive learning ✅
31 InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective 提出InfoCL以解决持续文本分类中的灾难性遗忘问题 representation learning contrastive learning ✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
32 NEWTON: Are Large Language Models Capable of Physical Reasoning? 提出NEWTON以评估大型语言模型的物理推理能力 manipulation large language model
33 Large Language Models for Propaganda Detection 利用大型语言模型检测数字社会中的宣传信息 manipulation large language model
34 No Pitch Left Behind: Addressing Gender Unbalance in Automatic Speech Recognition through Pitch Manipulation 提出基于音高操控的数据增强技术以解决ASR中的性别不平衡问题 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
35 Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models 通过元认知提示减少大语言模型的心理理论预测误差 affordance large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页