cs.CL（2024-02-20）

📊 共 55 篇论文 | 🔗 10 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (48 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (48 篇)

#题目一句话要点标签🔗⭐
1 CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models 提出CIF-Bench以评估大型语言模型在中文任务中的泛化能力 large language model instruction following
2 Learning to Check: Unleashing Potentials for Self-Correction in Large Language Models 提出Step CoT Check以提升大语言模型的自我纠错能力 large language model chain-of-thought ✅
3 Me LLaMA: Foundation Large Language Models for Medical Applications 提出Me-LLaMA以解决医学语言理解挑战 large language model foundation model
4 Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance 提出小型专用模型在有限标注样本下超越大型通用模型的方法 large language model
5 Is the System Message Really Important to Jailbreaks in Large Language Models? 提出系统消息进化算法以增强大语言模型的安全性 large language model
6 TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning 提出TreeEval以解决大型语言模型评估中的数据泄露问题 large language model ✅
7 Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning 比较人类与大型语言模型的推理策略以提升推理能力 large language model
8 GlórIA -- A Generative and Open Large Language Model for Portuguese 提出GlórIA以解决葡萄牙语LLM稀缺问题 large language model
9 Can Large Language Models be Used to Provide Psychological Counselling? An Analysis of GPT-4-Generated Responses Using Role-play Dialogues 利用GPT-4生成心理咨询对话以应对心理健康挑战 large language model
10 FinBen: A Holistic Financial Benchmark for Large Language Models 提出FinBen以解决金融领域LLM评估不足问题 large language model ✅
11 CHATATC: Large Language Model-Driven Conversational Agents for Supporting Strategic Air Traffic Flow Management 提出CHATATC以支持战略空中交通流管理问题 large language model
12 Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text 提出结构引导提示以解决多步推理问题 large language model
13 Investigating Cultural Alignment of Large Language Models 提出人类文化对大型语言模型的对齐方法以解决文化多样性问题 large language model
14 Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation 提出方法以缓解情感支持对话中的偏好偏差问题 large language model
15 Stable Knowledge Editing in Large Language Models 提出StableKE以解决大语言模型知识编辑不稳定问题 large language model
16 SiLLM: Large Language Models for Simultaneous Machine Translation 提出SiLLM以解决同步机器翻译中的时序决策问题 large language model
17 Prompt Stealing Attacks Against Large Language Models 提出提示盗取攻击以解决大型语言模型安全问题 large language model
18 Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations 提出Spoken-LLM以解决口语对话中风格差异响应问题 large language model
19 OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification 提出OWSM-CTC以解决多任务语音识别与翻译问题 foundation model
20 AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning 提出AgentMD以解决临床计算器使用效率低下问题 large language model chain-of-thought
21 Benchmarking Retrieval-Augmented Generation for Medicine 提出MIRAGE基准以优化医学领域的检索增强生成系统 large language model chain-of-thought
22 The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis 分析多语言上下文学习中示例的影响 large language model instruction following
23 $R^3$: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks 提出$R^3$以解决Text-to-SQL任务中的一致性问题 large language model chain-of-thought
24 Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models 提出GLAN方法以生成大规模合成指令数据 large language model instruction following
25 Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A 提出多选问答中LLMs概率校准问题的解决方案 large language model
26 Soft Self-Consistency Improves Language Model Agents 提出软自一致性方法以提升语言模型代理的性能 large language model
27 Instruction-tuned Language Models are Better Knowledge Learners 提出预指令调优方法以提升知识学习能力 large language model
28 HumanEval on Latest GPT Models -- 2024 利用最新GPT模型提升程序合成能力 large language model ✅
29 SoftQE: Learned Representations of Queries Expanded by LLMs 提出SoftQE以提升查询编码器的检索性能 large language model
30 CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation 提出CMDAG数据集以提升中文隐喻生成能力 chain-of-thought ✅
31 Event-level Knowledge Editing 提出事件级知识编辑以解决传统知识更新效率低下问题 large language model
32 Identifying Semantic Induction Heads to Understand In-Context Learning 提出语义归纳头以理解上下文学习问题 large language model
33 Can GNN be Good Adapter for LLMs? 提出GraphAdapter以高效建模文本属性图 large language model
34 PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs 提出PANDA以增强大语言模型的领域特定能力 large language model
35 An LLM Maturity Model for Reliable and Transparent Text-to-Query 提出LLM成熟度模型以解决文本查询的可靠性与透明性问题 large language model
36 A Dual-Prompting for Interpretable Mental Health Language Models 提出双重提示方法以提升心理健康语言模型的可解释性 large language model
37 A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion 提出统一的框架以解决实体集扩展与分类法扩展问题 large language model
38 Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems 提出DAUS以解决任务导向对话系统用户模拟的不足问题 large language model
39 EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries 提出EvoGrad以解决Winograd Schema Challenge中的动态数据集问题 large language model
40 A Simple but Effective Approach to Improve Structured Language Model Output for Information Extraction 提出G&O方法以提升结构化语言模型在信息提取中的表现 large language model
41 RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian 提出RoCode数据集以评估罗马尼亚语代码智能 large language model
42 What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents 提出CosmoAgent以模拟人类与外星文明的复杂互动 large language model ✅
43 Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries 提出基于文本摘要的对话检索方法以解决少样本对话状态追踪问题 large language model
44 SoMeLVLM: A Large Vision Language Model for Social Media Processing 提出SoMeLVLM以解决社交媒体处理中的多模态挑战 multimodal
45 Understanding the effects of language-specific class imbalance in multilingual fine-tuning 提出语言特定类别不平衡的解决方案以改善多语言微调效果 large language model
46 Code Needs Comments: Enhancing Code LLMs with Comment Augmentation 提出代码注释增强方法以提升代码LLM性能 large language model
47 Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation 提出RUTEd评估以解决语言模型偏见评估不足问题 large language model
48 StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing 提出StyleDubber以解决电影配音中的时间与情感对齐问题 multimodal ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
49 ELAD: Explanation-Guided Large Language Models Active Distillation 提出ELAD框架以优化大语言模型的知识蒸馏 distillation large language model
50 A Survey on Knowledge Distillation of Large Language Models 综述知识蒸馏在大型语言模型中的应用与挑战 distillation large language model ✅
51 MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models 提出MoELoRA以解决大语言模型微调效率低下问题 contrastive learning large language model
52 Large Language Model-based Human-Agent Collaboration for Complex Task Solving 提出基于大语言模型的人机协作方法以解决复杂任务 reinforcement learning offline reinforcement learning large language model ✅
53 Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive 提出DPO-Positive以解决DPO在偏好优化中的失败模式问题 DPO large language model
54 PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning 提出PromptKD以解决生成语言模型知识蒸馏问题 distillation large language model instruction following

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

#题目一句话要点标签🔗⭐
55 TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text 提出Text2Afford以解决语言模型对物体可供性预测的不足问题 affordance ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页