cs.CL（2023-11-16）

📊 共 58 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (54 🔗9) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (54 篇)

#题目一句话要点标签🔗⭐
1 Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models 提出GE-Reasoning方法以优化大语言模型的多步推理 large language model chain-of-thought
2 Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models 提出零-shot文本消毒技术以解决敏感信息处理问题 large language model
3 When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models 评估系统提示中的角色对大型语言模型性能的影响 large language model ✅
4 Improving the Generation Quality of Watermarked Large Language Models via Word Importance Scoring 提出水印重要性评分方法以提升水印大语言模型生成质量 large language model
5 ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code 提出ML-Bench以评估大语言模型在代码理解中的表现 large language model ✅
6 MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning 提出MedAgents框架以解决医疗领域零-shot推理问题 large language model ✅
7 Investigating Data Contamination in Modern Benchmarks for Large Language Models 提出数据污染检测方法以提升大语言模型评估准确性 large language model
8 You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments 评估大型语言模型在心理测量工具上的可靠性问题 large language model
9 BLT: Can Large Language Models Handle Basic Legal Text? 提出法律文本处理基准以提升LLM在法律领域的表现 large language model
10 MacGyver: Are Large Language Models Creative Problem Solvers? 提出MACGYVER数据集以评估大型语言模型的创造性问题解决能力 large language model
11 Structured Chemistry Reasoning with Large Language Models 提出StructChem以提升大语言模型在化学推理中的能力 large language model ✅
12 Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models 提出多模态图编码方法以提升大语言模型的图理解能力 large language model
13 Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking 提出认知过载攻击以破解大型语言模型的安全性问题 large language model
14 Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning 提出Complex-TR数据集以增强大语言模型的时间推理能力 large language model ✅
15 SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models 提出SUQL以解决混合数据访问的对话搜索问题 large language model
16 Large Language Models for Propaganda Span Annotation 利用大型语言模型进行宣传跨度标注以提升内容理解 large language model
17 How Far Can We Extract Diverse Perspectives from Large Language Models? 提出基于标准的提示技术以从大型语言模型中提取多样化观点 large language model
18 Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations 提出测试时后门攻击防御机制以解决黑箱大语言模型安全问题 large language model
19 The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics 通过语言启发式词汇修剪提升大语言模型推理效率 large language model
20 R-Tuning: Instructing Large Language Models to Say `I Don't Know' 提出R-Tuning以解决大型语言模型的知识缺失问题 large language model ✅
21 Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition 利用大型语言模型生成少量训练示例以提升谬误识别能力 large language model
22 Effective Large Language Model Adaptation for Improved Grounding and Citation Generation 提出AGREE框架以解决LLM生成虚假答案的问题 large language model
23 GEE! Grammar Error Explanation with Large Language Models 提出语法错误解释系统以提升语言学习效果 large language model
24 The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents 探讨LLM代理在党派偏见下的集体智慧表现 large language model chain-of-thought
25 Event Causality Is Key to Computational Story Understanding 提出事件因果关系识别方法以提升计算故事理解能力 large language model multimodal ✅
26 P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models 提出P^3SUM以解决新闻摘要中作者意图保留问题 large language model
27 Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge 提出UnknownBench以评估LLMs在知识缺口下的不确定性表达 large language model
28 Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs 评估大语言模型在主观判断中的社会人口学偏差 large language model ✅
29 Predictive Minds: LLMs As Atypical Active Inference Agents 将大型语言模型视为主动推理代理以提升自我意识 large language model
30 ChatGPT-3.5, ChatGPT-4, Google Bard, and Microsoft Bing to Improve Health Literacy and Communication in Pediatric Populations and Beyond 利用大型语言模型提升儿童及其他人群的健康素养 large language model
31 ConceptPsy:A Benchmark Suite with Conceptual Comprehensiveness in Psychology 提出ConceptPsy以解决心理学领域评估不足的问题 large language model
32 Interpreting User Requests in the Context of Natural Language Standing Instructions 提出基于用户持续指令的对话建模以改善自然语言接口 large language model
33 Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination? 提出EureQA以解决LLMs推理中的语义偏差问题 large language model
34 Multi-Step Dialogue Workflow Action Prediction 提出多步骤对话工作流动作预测以提升任务自动化 large language model
35 BrainLLM: Generative Language Decoding from Brain Recordings 提出BrainLLM以解决脑机接口语言生成问题 large language model
36 WatME: Towards Lossless Watermarking Through Lexical Redundancy 提出WatME以解决文本水印对LLM能力影响的问题 large language model
37 Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks 通过主动学习提升领域特定任务的注释效率 large language model
38 PixT3: Pixel-based Table-To-Text Generation 提出PixT3以解决表格到文本生成中的线性化问题 multimodal
39 DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents 提出DocMath-Eval以评估LLMs在理解长文档中的数学推理能力 chain-of-thought
40 $\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning 提出BeInfo以解决信息检索对话中的事实性问题 large language model
41 FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains 提出FinanceMath以评估金融领域知识密集型数学推理能力 chain-of-thought
42 OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking 提出OrchestraLLM以提高对话状态跟踪的效率与性能 large language model
43 On the Impact of Calibration Data in Post-training Quantization and Pruning 研究校准数据对后训练量化与剪枝的影响 large language model
44 GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding 提出GenCodeSearchNet以评估编程语言理解的泛化能力 large language model
45 Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability 研究ChatGPT语言识别能力，揭示其在多语言处理中的不足 large language model
46 Inducing Political Bias Allows Language Models Anticipate Partisan Reactions to Controversies 提出单一模型以解决政治偏见预测问题 large language model
47 Evaluating In-Context Learning of Libraries for Code Generation 评估代码生成库的上下文学习能力 large language model
48 Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning 提出增量效用评估方法以优化少样本上下文学习 large language model
49 Simulating Opinion Dynamics with Networks of LLM-based Agents 基于大语言模型的代理模拟人类意见动态 large language model
50 GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks 提出GistScore以优化上下文示例选择问题 large language model
51 Self-Contradictory Reasoning Evaluation and Detection 提出自我矛盾推理评估与检测方法以提升LLM的推理可靠性 large language model
52 LifeTox: Unveiling Implicit Toxicity in Life Advice 提出LifeTox以解决隐性毒性检测问题 large language model ✅
53 TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction 提出TextEE基准以解决事件抽取评估不一致性问题 large language model
54 Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents 提出生成-检索-生成模型以提升对话代理性能 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
55 FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models 提出FollowEval基准以评估大型语言模型的指令遵循能力 manipulation large language model instruction following

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
56 MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts 提出MMoE以解决多模态交互建模不足问题 HuMoR multimodal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
57 Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion 提出EmoTrigger数据集以评估情感预测模型对情感触发因素的考虑 motion prediction 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🔗⭐
58 To be or not to be? an exploration of continuously controllable prompt engineering 提出ControlPE以解决提示工程控制精度不足的问题 distillation large language model chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页