cs.CL（2023-11-15）

📊 共 70 篇论文 | 🔗 15 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (60 🔗12) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (60 篇)

#题目一句话要点标签🔗⭐
1 Comparing Generalization in Learning with Limited Numbers of Exemplars: Transformer vs. RNN in Attractor Dynamics 比较Transformer与RNN在有限样本学习中的泛化能力 large language model
2 XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs 提出XplainLLM以解决大型语言模型推理透明性问题 large language model
3 Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis 通过因果公平分析探讨语言模型中的政治偏见归因 large language model ✅
4 Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization 提出指令可控文本摘要基准以评估大型语言模型的生成与评估能力 large language model instruction following
5 MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning 提出MMC数据集以解决图表理解中的多模态挑战 large language model multimodal ✅
6 Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization 通过目标优先级整合防御大语言模型的越狱攻击 large language model instruction following ✅
7 GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models 提出GRASP基准以评估多模态语言模型的语言基础与物理理解能力 large language model multimodal
8 The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task 提出链式思维方法以提升复杂视觉语言推理任务的性能 chain-of-thought
9 Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification 提出Ever方法以实时验证和修正大语言模型的幻觉问题 large language model
10 Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models 提出Zooter以解决大语言模型的高计算开销问题 large language model
11 When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour 研究大型语言模型的谄媚行为及其对可靠性的影响 large language model
12 Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization 研究修剪大语言模型中的幻觉现象以提升摘要生成效果 large language model
13 Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models 提出Symbol-LLM以解决大型语言模型的符号知识理解问题 large language model ✅
14 Assessing Translation capabilities of Large Language Models involving English and Indian Languages 评估大型语言模型在英印语言翻译中的能力 large language model
15 How Well Do Large Language Models Truly Ground? 提出严格的基础定义以提升大型语言模型的可靠性 large language model
16 Identifying Linear Relational Concepts in Large Language Models 提出线性关系概念以识别大语言模型中的人类可解释概念 large language model
17 Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values 提出基本价值对齐范式以解决大语言模型的价值定义问题 large language model
18 Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains 研究大型语言模型在概念标注指南中的应用能力 large language model
19 Investigating the Emergent Audio Classification Ability of ASR Foundation Models 提出无监督重标定方法以提升ASR模型的零-shot音频分类能力 foundation model
20 LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback 提出LLMRefine以优化大语言模型输出质量 large language model
21 Contrastive Chain-of-Thought Prompting 提出对比链式思维提示以增强语言模型推理能力 chain-of-thought
22 PsyEval: A Suite of Mental Health Related Tasks for Evaluating Large Language Models 提出PsyEval以评估大型语言模型在心理健康领域的表现 large language model
23 ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models 提出ContraDoc以解决长文档中的自我矛盾问题 large language model ✅
24 Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers 提出Pearl以解决大型语言模型个性化写作助手问题 large language model
25 CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models 提出Clean-Eval以解决大语言模型评估中的数据污染问题 large language model
26 Exploring the Potential of Large Language Models in Computational Argumentation 评估大型语言模型在计算论证中的应用潜力 large language model
27 Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models 提出无监督自我提升框架以解决零样本命名实体识别问题 large language model ✅
28 Large Language Models are legal but they are not: Making the case for a powerful LegalLLM 提出法律领域专用LLM以解决现有模型性能不足问题 large language model
29 Disinformation Capabilities of Large Language Models 研究大型语言模型的虚假信息生成能力 large language model
30 StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving 提出StrategyLLM以解决现有提示方法的通用性与一致性问题 large language model
31 Enhancing Emergency Decision-making with Knowledge Graphs and Large Language Models 提出E-KELL系统以提升应急决策支持能力 large language model
32 Towards A Unified View of Answer Calibration for Multi-Step Reasoning 提出统一视角的答案校准方法以提升多步推理能力 large language model chain-of-thought
33 How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities 提出advCoU策略以评估开源LLM的可信度 large language model instruction following
34 Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets 提出一种方法评估语言模型在多样挑战集上的鲁棒性 large language model chain-of-thought
35 PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning 提出PLUG方法以解决低资源语言指令调优问题 large language model instruction following ✅
36 ToolTalk: Evaluating Tool-Usage in a Conversational Setting 提出ToolTalk基准以评估对话环境中的工具使用 large language model ✅
37 Data Similarity is Not Enough to Explain Language Model Performance 探讨数据相似性不足以解释语言模型性能的复杂性 large language model
38 LOKE: Linked Open Knowledge Extraction for Automated Knowledge Graph Construction 提出LOKE以解决开放信息提取在知识图谱构建中的不足 large language model
39 Empirical evaluation of Uncertainty Quantification in Retrieval-Augmented Language Models for Science 评估不确定性量化在科学检索增强语言模型中的应用 large language model ✅
40 Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"? 温度缩放惊讶度估计提升人类阅读时间预测准确性 large language model
41 Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models 提出Chain-of-Noting以解决检索增强语言模型的鲁棒性问题 large language model
42 TableLlama: Towards Open Large Generalist Models for Tables 提出TableLlama以解决表格任务的通用性问题 large language model
43 Fusion-Eval: Integrating Assistant Evaluators with LLMs 提出Fusion-Eval以解决自然语言系统评估问题 large language model
44 How Vocabulary Sharing Facilitates Multilingualism in LLaMA? 通过词汇共享提升LLaMA的多语言能力 large language model ✅
45 Assessing Knowledge Editing in Language Models via Relation Perspective 提出RaKE基准以解决关系中心知识编辑问题 large language model
46 When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks 探讨ICL在复杂任务中的局限性及其原因 large language model
47 Transformers in the Service of Description Logic-based Contexts 构建DELTA_D数据集以提升基于Transformer的推理能力 large language model
48 Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization 提出参数高效层以解决零-shot跨语言摘要问题 large language model
49 GENEVA: GENErating and Visualizing branching narratives using LLMs 提出GENEVA工具以生成和可视化分支叙事 large language model
50 Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models 通过结构性启动揭示多语言模型中的抽象语法表示 large language model
51 SiRA: Sparse Mixture of Low Rank Adaptation 提出SiRA以提升大语言模型的参数高效调优 large language model
52 Grounding Gaps in Language Model Generations 提出对话行为度量以解决语言模型生成中的共识缺失问题 large language model
53 Social Meme-ing: Measuring Linguistic Variation in Memes 构建多模态管道以分析表情包中的语言变异 multimodal
54 MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation 提出MAVEN-Arg以解决事件理解数据集缺失问题 large language model ✅
55 Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers 提出Factcheck-Bench以解决自动事实核查的评估问题 large language model ✅
56 Speculative Contrastive Decoding 提出投机对比解码以提升语言模型解码效率与质量 large language model
57 HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation 提出HeLM模型以解决表格到文本生成中的信息泄露问题 large language model
58 Thread of Thought Unraveling Chaotic Contexts 提出Thread of Thought策略以解决混乱上下文问题 large language model
59 Token Prediction as Implicit Classification to Identify LLM-Generated Text 提出基于下一个标记预测的隐式分类方法以识别LLM生成文本 large language model
60 Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory 提出Think-in-Memory机制以解决LLMs的长期记忆问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
61 Deep Representation Learning for Open Vocabulary Electroencephalography-to-Text Decoding 提出深度学习框架以解决开放词汇EEG解码问题 representation learning open-vocabulary open vocabulary
62 Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation 提出多阶段协作知识蒸馏方法以解决半监督序列生成问题 distillation large language model
63 Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models 提出自我评估能力蒸馏方法以提升小型语言模型性能 distillation large language model chain-of-thought
64 Distilling Rule-based Knowledge into Large Language Models 提出基于规则的知识蒸馏方法以提升大语言模型的学习效率 distillation large language model
65 Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling 提出输入澄清集成方法以解决大型语言模型的不确定性分解问题 predictive model large language model ✅
66 Aligning Neural Machine Translation Models: Human Feedback in Training and Inference 提出基于人类反馈的强化学习方法以提升机器翻译质量 reinforcement learning RLHF large language model
67 R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces 提出R-Spin以解决说话者和噪声不变性问题 representation learning
68 CLIMB: Curriculum Learning for Infant-inspired Model Building 提出基于课程学习的模型构建方法以提升语言模型性能 curriculum learning
69 Safer-Instruct: Aligning Language Models with Automated Preference Data 提出Safer-Instruct以解决偏好数据自动生成问题 reinforcement learning RLHF ✅
70 Accelerating Toeplitz Neural Network with Constant-time Inference Complexity 提出Toeplitz神经网络转化为状态空间模型以实现常数时间推理 SSM state space model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页