cs.CL（2024-04-04）

📊 共 28 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) (22 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models 提出可视化思维方法以增强大语言模型的空间推理能力 large language model multimodal ✅
2 nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States 利用Flan-T5和链式思维解决对话中的情感原因推理问题 large language model chain-of-thought ✅
3 Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models 提出基于嵌入的自适应检索增强生成方法以优化LLM性能 large language model
4 Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding 通过理解逻辑谬误提升大语言模型的逻辑推理能力 large language model
5 The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models 提出相关解释信度度量以解决大语言模型解释可信度问题 large language model
6 CONFLARE: CONFormal LArge language model REtrieval 提出CONFLARE以量化检索不确定性，提升RAG框架的可信度 large language model
7 An Investigation into Misuse of Java Security APIs by Large Language Models 评估大型语言模型在Java安全API生成中的可靠性 large language model
8 Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models 提出KNOT数据集以解决大型语言模型中的知识冲突问题 large language model ✅
9 How Easily do Irrelevant Inputs Skew the Responses of Large Language Models? 提出框架评估大语言模型对无关信息的鲁棒性 large language model ✅
10 Probing Large Language Models for Scalar Adjective Lexical Semantics and Scalar Diversity Pragmatics 探讨大型语言模型在标量形容词语义与多样性语用学中的表现 large language model
11 Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers 评估大型语言模型在文本排序中的公平性问题 large language model
12 Evaluating LLMs at Detecting Errors in LLM Responses 提出ReaLMistake基准以解决LLM响应错误检测问题 large language model instruction following ✅
13 Training LLMs over Neurally Compressed Text 提出Equal-Info Windows以解决神经压缩文本训练LLM的问题 large language model
14 Template-Based Probes Are Imperfect Lenses for Counterfactual Bias Evaluation in LLMs 提出模板探针以解决大型语言模型偏见评估问题 large language model
15 Bias Amplification in Language Model Evolution: An Iterated Learning Perspective 提出迭代学习框架以解决语言模型偏见放大问题 large language model
16 SHROOM-INDElab at SemEval-2024 Task 6: Zero- and Few-Shot LLM-Based Classification for Hallucination Detection 提出SHROOM-INDElab以解决幻觉检测问题 large language model
17 Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph 提出一种框架以解码LLM中的事实知识用于句子级声明验证 large language model
18 Evaluating Generative Language Models in Information Extraction as Subjective Question Correction 提出SQC-Score以解决信息提取中的评估不准确问题 large language model ✅
19 Generative AI and Teachers -- For Us or Against Us? A Case Study 调查大学教师对生成性人工智能的使用及其影响 large language model
20 Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions 通过多模态辅导系统提出语言学习支架方法 large language model
21 Edisum: Summarizing and Explaining Wikipedia Edits at Scale 提出Edisum以解决维基百科编辑摘要缺失问题 large language model
22 Towards Pareto Optimal Throughput in Small Language Model Serving 提出小语言模型服务的帕累托最优吞吐量方法 large language model

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

#题目一句话要点标签🔗⭐
23 Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought 提出LM-Guided CoT框架以提升大语言模型推理能力 reinforcement learning distillation large language model
24 Conversational Disease Diagnosis via External Planner-Controlled Large Language Models 提出基于外部规划器的LLM对话式疾病诊断系统 reinforcement learning large language model
25 AutoWebGLM: A Large Language Model-based Web Navigating Agent 提出AutoWebGLM以解决复杂网页导航问题 reinforcement learning large language model ✅
26 Locating and Editing Factual Associations in Mamba 研究Mamba模型中的事实关联定位与编辑机制 Mamba state space model
27 How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes 提出多任务学习策略以提升变换器的上下文学习能力 curriculum learning large language model ✅
28 Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation 提出基于生成推理和知识蒸馏的事件共指建模方法 distillation ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页