cs.CL（2023-11-14）

📊 共 44 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) (37 🔗9) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (37 篇)

#题目一句话要点标签🔗⭐
1 Instruction-Following Evaluation for Large Language Models 提出指令跟随评估基准以解决大型语言模型评估标准化问题 large language model instruction following ✅
2 Are Large Language Models Temporally Grounded? 探讨大型语言模型的时间基础性问题 large language model chain-of-thought ✅
3 Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning 提出半结构化思维链以整合多源知识提升语言模型推理能力 large language model chain-of-thought
4 Automated title and abstract screening for scoping reviews using the GPT-4 Large Language Model 提出GPTscreenR以自动化文献筛选过程 large language model chain-of-thought
5 AfroBench: How Good are Large Language Models on African Languages? 提出AfroBench以评估大型语言模型在非洲语言上的表现 large language model ✅
6 Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective 提出新训练方法以解决大语言模型生成有害信息的问题 large language model
7 A Survey of Confidence Estimation and Calibration in Large Language Models 综述大语言模型的置信度估计与校准方法 large language model
8 MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration 提出MAgIC框架以评估多智能体环境中的LLMs能力 large language model ✅
9 Efficient Continual Pre-training for Building Domain Specific Large Language Models 提出持续预训练方法以高效构建领域特定的大型语言模型 large language model
10 Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models 提出选择镜头策略以提升少样本学习中的公平性 large language model
11 Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning 提出Chain-of-Opinion以解决大语言模型对人类意见预测的挑战 large language model
12 SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models 提出SimpleSafetyTests以识别大型语言模型的安全风险 large language model
13 On-the-Fly Fusion of Large Language Models and Machine Translation 提出即时融合机器翻译模型与大语言模型以提升翻译质量 large language model
14 How Well Do Large Language Models Understand Syntax? An Evaluation by Asking Natural Language Questions 评估大型语言模型对句法理解的能力 large language model
15 A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily 提出ReNeLLM框架以自动生成有效的越狱提示 large language model ✅
16 Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster 提出FastCoT以加速大语言模型推理过程 chain-of-thought
17 Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration 提出多代理协作策略以提升大语言模型推理能力 large language model
18 Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models 提出F-Learning以解决大语言模型知识更新问题 large language model
19 Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning 提出自演化多样数据采样方法以提高指令调优效率 large language model instruction following ✅
20 Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts 提出跨语言思维树方法以解决多步推理问题 large language model chain-of-thought
21 Predicting Text Preference Via Structured Comparative Reasoning 提出结构化比较推理方法以提升文本偏好预测准确性 large language model chain-of-thought
22 How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection 揭示任务导向约束对LLM生成文本检测的影响 large language model instruction following
23 Low-Rank Adaptation for Multilingual Summarization: An Empirical Study 提出低秩适应方法以解决多语言摘要任务中的调优挑战 large language model
24 GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer 提出GLiNER以解决传统命名实体识别模型的局限性 large language model
25 Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game 提出对抗偏好优化框架以提升大语言模型的对齐效果 large language model ✅
26 Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models 提出Qwen-Audio以解决音频理解能力不足的问题 instruction following
27 CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation 提出CodeScope以解决现有代码理解与生成基准的不足问题 large language model ✅
28 Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios 提出自一致性方法以改善语言模型推理能力 chain-of-thought
29 LLatrieval: LLM-Verified Retrieval for Verifiable Generation 提出LLatrieval以解决可验证生成中的检索瓶颈问题 large language model
30 Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment 提出FlipFlop实验以分析大型语言模型的多轮对话行为 large language model
31 UT5: Pretraining Non autoregressive T5 with unrolled denoising 提出UT5以解决自回归模型的性能瓶颈问题 large language model
32 AI-generated text boundary detection with RoFT 提出基于RoFT的文本边界检测方法以解决人机混合文本识别问题 large language model
33 MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China 提出MC$^2$以解决中国少数民族语言NLP的透明性与文化意识问题 large language model
34 All Data on the Table: Novel Dataset and Benchmark for Cross-Modality Scientific Information Extraction 提出半监督管道以解决跨模态科学信息提取问题 large language model
35 SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks 提出SAIE框架以增强大语言模型的训练效果 large language model
36 It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction 提出一种合成查询生成方法以改善零样本相关性预测 large language model
37 Fair Abstractive Summarization of Diverse Perspectives 提出公平抽象摘要方法以解决多元观点总结问题 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🔗⭐
38 Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding 提出直接偏好优化以提升神经机器翻译性能 reinforcement learning DPO direct preference optimization
39 Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning 通过检索引导对比学习提升仇恨表情包检测能力 contrastive learning multimodal
40 Brain-Driven Representation Learning Based on Diffusion Model 提出基于扩散模型的脑驱动表示学习以解决EEG信号分析问题 representation learning
41 Sinkhorn Transformations for Single-Query Postprocessing in Text-Video Retrieval 提出Sinkhorn变换以解决单查询文本-视频检索后处理问题 DRL multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
42 The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language 提出CLAP-IPA以解决多语言关键词识别与强制对齐问题 open-vocabulary open vocabulary
43 Spot: A Natural Language Interface for Geospatial Searches in OSM 提出Spot以解决OSM数据查询的可访问性问题 semantic mapping semantic map

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
44 A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts 探讨文本改写中的作者归属问题 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页