cs.CL（2025-04-17）

📊 共 35 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (33 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (33 篇)

#题目一句话要点标签🔗⭐
1 ChatEXAONEPath: An Expert-level Multimodal Large Language Model for Histopathology Using Whole Slide Images ChatEXAONEPath：一种用于组织病理学WSI的专家级多模态大语言模型 large language model multimodal
2 Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration 提出GeoGen与GeoLogic，提升多模态LLM在几何问题求解中的能力 large language model multimodal ✅
3 GeoSense: Evaluating Identification and Application of Geometric Principles in Multimodal Reasoning GeoSense：提出用于评估多模态LLM几何推理能力的新基准 large language model multimodal
4 Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo 提出基于序列蒙特卡洛的语言模型控制框架，提升在语法和语义约束下的文本生成性能。 large language model
5 Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback 提出无需反馈的重试机制，提升大语言模型推理能力，降低计算成本。 large language model
6 DIDS: Domain Impact-aware Data Sampling for Large Language Model Training DIDS：领域感知的数据采样方法，用于提升大语言模型训练效果 large language model ✅
7 Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models 通过干预先验分布提升大语言模型在确定性任务中的表现 large language model
8 CPG-EVAL: A Multi-Tiered Benchmark for Evaluating the Chinese Pedagogical Grammar Competence of Large Language Models CPG-EVAL：用于评估大语言模型汉语教学语法能力的基准 large language model
9 SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation 提出基于因果分析和分层优化的选择性遗忘方法，提升LLM数据隐私保护能力。 large language model
10 Benchmarking Multi-National Value Alignment for Large Language Models 提出NaVAB基准，评估大型语言模型在多国价值观上的对齐程度 large language model
11 Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models 提出信息增益引导的因果干预框架，用于自主消除大语言模型中的偏见 large language model
12 Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge Pandora：一种代码驱动的大语言模型Agent，用于统一推理多种结构化知识 large language model
13 How Large Language Models Are Changing MOOC Essay Answers: A Comparison of Pre- and Post-LLM Responses 分析LLM对MOOC论文作答的影响：对比ChatGPT前后学生提交的AI伦理论文 large language model
14 ConExion: Concept Extraction with Large Language Models ConExion：利用大型语言模型进行概念抽取，提升领域覆盖评估和本体学习。 large language model ✅
15 Chinese-Vicuna: A Chinese Instruction-following Llama-based Model Chinese-Vicuna：一种基于LLaMA的中文指令跟随模型，针对低资源环境。 instruction following
16 Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment 提出Persona-judge，通过token级自判别实现大语言模型的个性化对齐。 large language model
17 Deep literature reviews: an application of fine-tuned language models to migration research 提出基于微调语言模型的深度文献综述框架，应用于人口迁移研究。 large language model
18 Retrieval-Augmented Generation with Conflicting Evidence 提出MADAM-RAG，解决检索增强生成中冲突证据带来的歧义、噪声和错误信息问题 large language model
19 Accuracy is Not Agreement: Expert-Aligned Evaluation of Crash Narrative Classification Models 揭示事故叙事分类中准确率与专家一致性的悖论，并探索LLM在安全关键任务中的应用潜力。 large language model
20 Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation 提出自注意力检索增强的方面级摘要生成框架，解决大模型token限制和幻觉问题。 large language model
21 Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild 提出Swin-VIB框架，解决检索增强LLM中知识冲突导致的响应不确定性问题 large language model
22 ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs ImPart：面向LLM的基于重要性的Delta稀疏化方法，提升模型压缩与合并效果 large language model
23 Sparks of Science: Hypothesis Generation Using Structured Paper Data 提出HypoGen数据集，用于训练模型生成更具创新性和可行性的科学假设。 foundation model
24 MAIN: Mutual Alignment Is Necessary for instruction tuning 提出MAIN框架，通过互对齐提升指令调优中指令-响应对的质量。 large language model
25 ViClaim: A Multilingual Multilabel Dataset for Automatic Claim Detection in Videos ViClaim：一个用于视频自动声明检测的多语言多标签数据集 multimodal
26 Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks 提出MLRBench，用于评估LLM在多语言长文本上的推理能力，超越简单检索。 large language model
27 Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation 评估LLM在艺术语境下的表现：评论生成与心理理论能力评估 large language model
28 Data-efficient LLM Fine-tuning for Code Generation 提出数据选择与动态token打包策略，提升代码生成LLM微调效率与性能 large language model
29 GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs GRAIL：基于梯度的自适应解学习框架，用于LLM中的隐私和版权保护 large language model
30 Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation 提出基于分层合成数据生成的大语言模型长文本扩展方法，实现百万token上下文处理。 large language model
31 SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs SOLAR框架：通过建模价值冲突与权衡，刻画个体主观性 large language model
32 CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation 提出CDF-RAG，通过因果动态反馈增强RAG的推理能力和事实准确性 large language model
33 ELAB: Extensive LLM Alignment Benchmark in Persian Language ELAB：波斯语大型语言模型对齐的综合基准评测 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
34 LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard 微调LLM以提升金融任务性能，基于Open FinLLM排行榜 reinforcement learning DPO direct preference optimization
35 Energy-Based Reward Models for Robust Language Model Alignment 提出基于能量的奖励模型EBRM，提升语言模型对齐的鲁棒性和泛化性。 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页