cs.CL（2023-10-20）

📊 共 39 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) (32 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (32 篇)

#题目一句话要点标签🔗⭐
1 Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning 提出自促链式思维以解决开放领域多跳推理问题 large language model chain-of-thought
2 Why Can Large Language Models Generate Correct Chain-of-Thoughts? 提出两级层次图模型以提升大语言模型的思维链生成能力 large language model chain-of-thought
3 Challenges and Contributing Factors in the Utilization of Large Language Models (LLMs) 探讨大型语言模型的挑战与解决方案 large language model multimodal
4 Democratizing Reasoning Ability: Tailored Learning from Large Language Model 提出定制学习方法以提升小型语言模型的推理能力 large language model instruction following ✅
5 Visual Grounding Helps Learn Word Meanings in Low-Data Regimes 通过视觉引导提升低数据环境下的词汇学习效率 multimodal visual grounding
6 SALMONN: Towards Generic Hearing Abilities for Large Language Models 提出SALMONN以实现大型语言模型的通用听觉能力 large language model multimodal ✅
7 MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model 提出MoqaGPT以解决多模态开放域问答问题 large language model multimodal ✅
8 Semi-supervised multimodal coreference resolution in image narrations 提出半监督多模态共指消解方法以解决图像叙述中的挑战 multimodal
9 WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models 提出WordArt Designer以实现用户驱动的艺术排版合成 large language model
10 Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models 通过有限状态解码约束改进长语音翻译质量 large language model
11 Cache & Distil: Optimising API Calls to Large Language Models 提出神经缓存方法以优化大型语言模型API调用 large language model
12 AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models 提出AllTogether以提升大语言模型在网页导航中的效率 large language model
13 Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting 提出SocialSense框架以解决新闻媒体响应预测问题 large language model
14 ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search 提出ToolChain*以解决大语言模型中的动作空间导航问题 large language model
15 Copyright Violations and Large Language Models 探讨大型语言模型中的版权侵犯问题及其影响 large language model ✅
16 Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models 提出S3框架以解决数据合成中的分布差异问题 large language model
17 Self-Consistency of Large Language Models under Ambiguity 提出自一致性评估基准以解决大型语言模型一致性问题 large language model
18 Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks 提出混合评估方法以提升大语言模型在序列到序列任务中的评估准确性 large language model
19 StereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models 提出StereoMap框架以量化大型语言模型对人类刻板印象的认知 large language model
20 Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning 探讨大型语言模型在数学学习中的应用挑战与解决方案 large language model
21 The Perils & Promises of Fact-checking with Large Language Models 评估大型语言模型在自动化事实核查中的应用与局限性 large language model
22 Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning 提出适配器微调与上下文学习结合以提升机器翻译性能 large language model
23 Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking 提出基于大语言模型的零-shot查询概率模型以提升文档排名 large language model ✅
24 BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues 提出BotChat以评估大型语言模型的多轮对话能力 large language model instruction following ✅
25 Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks 评估语言模型隐私风险：聚焦摘要任务中的成员推断攻击 large language model
26 Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing 提出Evoke框架以提升大语言模型的提示编辑能力 large language model
27 MarineGPT: Unlocking Secrets of Ocean to the Public 提出MarineGPT以解决海洋领域特定知识缺乏问题 large language model
28 She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models 提出测试套件以确保大型语言模型的对齐与安全性 large language model
29 Explaining Interactions Between Text Spans 提出SpanEx数据集以解决自然语言理解中的交互解释问题 large language model
30 Implications of Annotation Artifacts in Edge Probing Test Datasets 揭示边缘探测测试数据集中的注释伪影问题 large language model
31 Ecologically Valid Explanations for Label Variation in NLI 构建LiveNLI数据集以揭示NLI标签变异的生态有效解释 large language model
32 Teaching Language Models to Self-Improve through Interactive Demonstrations 提出TriPosT算法以提升小型语言模型的自我改进能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
33 Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models 提出在线成本感知教师-学生框架以减少对大型语言模型的调用 teacher-student large language model
34 POSQA: Probe the World Models of LLMs with Size Comparisons 提出POSQA数据集以验证大型语言模型的现实理解能力 world model world models large language model
35 Tuna: Instruction Tuning using Feedback from Large Language Models 提出Tuna以解决指令调优模型响应多样性不足问题 reinforcement learning large language model ✅
36 DistillCSE: Distilled Contrastive Learning for Sentence Embeddings 提出DistillCSE框架以提升句子嵌入的对比学习效果 contrastive learning distillation
37 Multi-level Contrastive Learning for Script-based Character Understanding 提出多层对比学习框架以解决剧本角色理解问题 contrastive learning ✅
38 Coarse-to-Fine Dual Encoders are Better Frame Identification Learners 提出CoFFTEA以解决帧识别中的候选帧选择问题 representation learning contrastive learning curriculum learning ✅
39 Enhancing Abstractiveness of Summarization Models through Calibrated Distillation 提出DisCal以解决摘要模型抽象性不足问题 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页