cs.CL（2024-02-19）

📊 共 67 篇论文 | 🔗 17 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (58 🔗15) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (58 篇)

#题目一句话要点标签🔗⭐
1 RFBES at SemEval-2024 Task 8: Investigating Syntactic and Semantic Features for Distinguishing AI-Generated and Human-Written Texts 提出基于语义和句法特征的模型以区分AI生成与人类撰写文本 large language model
2 ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs 提出ArtPrompt以解决大语言模型安全性问题 large language model ✅
3 Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic 提出RESTA方法以解决语言模型安全性再对齐问题 instruction following ✅
4 In-Context Learning Demonstration Selection via Influence Analysis 提出InfICL以解决示范选择对ICL效果的影响问题 large language model
5 Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing? 提出统一模型以解决语音翻译中的多模态任务 large language model foundation model multimodal
6 AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling 提出AnyGPT以实现多模态统一处理 large language model multimodal ✅
7 RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning 提出RJUA-MedDQA以解决医疗文档问答与临床推理问题 large language model multimodal
8 Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion 提出浏览与集中方法以解决多图像理解问题 large language model multimodal
9 Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models 提出消除快捷神经元以提升大语言模型的知识编辑能力 large language model chain-of-thought
10 How Interpretable are Reasoning Explanations from Prompting Large Language Models? 提出多维度可解释性评估方法以提升大语言模型推理解释能力 large language model chain-of-thought ✅
11 Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations 提出结构化思维提示方法以提升内容基础的问答对话生成 large language model chain-of-thought
12 Emulated Disalignment: Safety Alignment for Large Language Models May Backfire! 提出模拟失调方法以逆转大型语言模型的安全对齐 large language model ✅
13 Stick to your Role! Stability of Personal Values Expressed in Large Language Models 提出价值稳定性研究以解决LLM评估不足问题 large language model
14 Purifying Large Language Models by Ensembling a Small Language Model 通过小型语言模型集成净化大型语言模型 large language model
15 Distilling Large Language Models for Text-Attributed Graph Learning 提出蒸馏大语言模型以解决文本属性图学习问题 large language model
16 Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Models 提出六项指标以提升大型语言模型的时间信息理解能力 large language model ✅
17 Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding 提出SPACE以加速大规模语言模型推理速度 large language model
18 Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models 提出IoE框架以提升大语言模型的自我修正能力 large language model ✅
19 Plato: Plan to Efficiently Decode for Large Language Model Inference 提出Plato以解决大语言模型推理效率低下问题 large language model
20 Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models 提出新框架评估输入长度对LLM推理性能的影响 large language model
21 Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One 提出FairThinking以解决大型语言模型的公平性问题 large language model
22 Do Large Language Models Understand Logic or Just Mimick Context? 探讨大型语言模型的逻辑理解能力与上下文模仿 large language model
23 EmoBench: Evaluating the Emotional Intelligence of Large Language Models 提出EmoBench以评估大型语言模型的情感智能 large language model ✅
24 High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models 利用预训练大语言模型提升资源匮乏语言的数据到文本生成能力 large language model
25 NEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms 提出NEO-BENCH以评估大语言模型对新词的鲁棒性 large language model
26 A Chinese Dataset for Evaluating the Safeguards in Large Language Models 提出中文数据集以评估大型语言模型的安全性 large language model ✅
27 Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models 提出Model Tailor以解决多模态大语言模型的灾难性遗忘问题 large language model
28 LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation 提出LEMMA以解决多模态虚假信息检测问题 multimodal
29 Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models 提出自动化数据集更新以解决大型语言模型评估问题 large language model ✅
30 ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding 提出ROSE方法以提升指令调优大语言模型的安全性 large language model
31 M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation 提出M2K-VDG以解决视频基础对话生成中的幻觉问题 multimodal
32 Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation 提出RetPO框架以优化对话检索中的查询重写 large language model
33 Head-wise Shareable Attention for Large Language Models 提出头部共享注意力机制以解决大语言模型参数冗余问题 large language model
34 Large Language Models for Stemming: Promises, Pitfalls and Failures 提出大语言模型进行词干提取以解决传统方法的局限性 large language model
35 GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations 提出GTBench以评估LLMs在博弈中的推理能力 large language model chain-of-thought
36 Transformer-based Causal Language Models Perform Clustering 提出基于Transformer的因果语言模型以提升指令跟随能力 large language model instruction following
37 Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection 提出Self-Filter方法以提升视觉语言模型的数据选择质量 large language model instruction following
38 CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation 提出CoCo-Agent以解决智能手机GUI自动化的认知能力不足问题 large language model multimodal ✅
39 IRR: Image Review Ranking Framework for Evaluating Vision-Language Models 提出IRR框架以评估视觉语言模型的多角度文本生成能力 multimodal
40 Modularized Networks for Few-shot Hateful Meme Detection 提出模块化网络以解决少样本仇恨表情检测问题 large language model
41 Reformatted Alignment 提出ReAlign以提升大语言模型与人类价值观的对齐 large language model ✅
42 Enabling Weak LLMs to Judge Response Reliability via Meta Ranking 提出Meta Ranking方法以提升弱LLM对响应可靠性的评估能力 large language model
43 EVOR: Evolving Retrieval for Code Generation 提出EVOR以解决静态知识库限制的问题 large language model
44 Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models 提出针对事实核查的精调Transformer模型以超越大型语言模型 large language model
45 Is It a Free Lunch for Removing Outliers during Pretraining? 提出一种改进的预训练方法以解决量化模型中的异常值问题 large language model
46 DiLA: Enhancing LLM Tool Learning with Differential Logic Layer 提出DiLA以增强LLM在逻辑推理中的能力 large language model
47 The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth 评估与提升大型语言模型作为LGBTQ青少年情感支持者的能力 large language model
48 Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages 提出NewsSerow以解决低资源语言环境监测问题 large language model
49 ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs 提出基于ChatGPT的数据增强方法以改善LLMs的去偏见效果 large language model
50 Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation 提出Standardize以解决内容生成中的标准对齐问题 large language model
51 Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation 提出演化AI集体以增强人类多样性和自我调节能力 large language model
52 Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding 提出Sequoia以解决大语言模型推理效率问题 large language model
53 Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers 通过更新Transformer前馈层中的键值记忆提升知识编辑能力 large language model ✅
54 Can LLMs Compute with Reasons? 提出归纳学习方法以提升小型语言模型的推理能力 large language model
55 Understanding the Therapeutic Relationship between Counselors and Clients in Online Text-based Counseling using LLMs 提出基于大语言模型的自动化方法以理解在线文本咨询中的治疗关系 large language model
56 Learning to Edit: Aligning LLMs with Knowledge Editing 提出学习编辑框架以解决大语言模型知识更新问题 large language model ✅
57 SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning 提出SIBO以解决大语言模型微调中的过平滑问题 large language model
58 FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema 提出FIPO以解决现有提示优化方法的泛化能力不足问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
59 Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation 提出直接大语言模型对齐方法以解决无人工标注偏好数据问题 RLHF DPO distillation
60 Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages 提出SDRRL以提升大语言模型的多语言能力 distillation large language model
61 CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation 提出CovRL以解决JavaScript引擎模糊测试中的覆盖指导问题 reinforcement learning large language model
62 HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text? 提出基于对比学习的单一模型以检测机器生成文本 contrastive learning large language model ✅
63 Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs 提出通用对数蒸馏损失以解决跨Tokenizer蒸馏问题 distillation large language model
64 Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation 提出注意力蒸馏以优化检索增强生成模型的训练 distillation large language model
65 Revisiting Knowledge Distillation for Autoregressive Language Models 提出自适应教学方法以改善自回归语言模型的知识蒸馏效果 distillation
66 Triple-Encoders: Representations That Fire Together, Wire Together 提出三重编码器以提高对话模型的效率与上下文理解 representation learning contrastive learning ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
67 Detecting misinformation through Framing Theory: the Frame Element-based Model 提出基于框架元素模型的误信息检测方法 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页