cs.CL（2025-03-25）

📊 共 27 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (22 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 ImF: Implicit Fingerprint for Large Language Models 提出隐式指纹ImF，增强大语言模型知识产权保护，抵抗对抗攻击。 large language model chain-of-thought
2 FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models FLEX：一个评估大型语言模型公平性鲁棒性的基准测试 large language model
3 DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models 提出DeCAP，通过上下文自适应提示生成来消除大语言模型零样本问答中的偏见 large language model
4 Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought Disorder 小规模神经语言模型在检测思维障碍方面优于大型语言模型 large language model
5 Generative Linguistics, Large Language Models, and the Social Nature of Scientific Success 探讨生成语言学在大型语言模型冲击下的发展策略：超越形式化，拥抱社会化 large language model
6 Rosetta-PL: Propositional Logic as a Benchmark for Large Language Model Reasoning 提出Rosetta-PL以评估大型语言模型的逻辑推理能力 large language model
7 Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays 大型语言模型在大学申请文书生成中存在对齐性和可控性问题 large language model
8 1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training 提出1.4百万开源蒸馏推理数据集以增强大型语言模型训练 large language model ✅
9 PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping PHEONA：用于评估基于大语言模型计算表型方法的框架 large language model
10 Linguistic Blind Spots of Large Language Models 揭示大型语言模型在细粒度语言标注任务中的能力盲区 large language model
11 DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific Charts 提出DomainCQA框架，用于构建领域知识密集型图表问答基准 large language model multimodal
12 SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings SCI-IDEA：利用上下文感知的Token和句子嵌入进行科学构思 large language model chain-of-thought
13 A Comparative Analysis of Word Segmentation, Part-of-Speech Tagging, and Named Entity Recognition for Historical Chinese Sources, 1900-1950 对比LLM与传统NLP工具在1900-1950年历史中文文本处理中的性能，解决分词、词性标注和命名实体识别问题。 large language model
14 HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detection HausaNLP提出一种基于ModernBERT的微调方法，用于细粒度的模型感知幻觉检测。 large language model
15 Scaling Laws of Synthetic Data for Language Models SynthLLM：通过图算法自动生成高质量合成数据，探索语言模型的可扩展性规律。 large language model
16 CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation CausalRAG：提出一种融合因果图的检索增强生成框架，提升知识密集型任务的准确性和可解释性。 large language model
17 Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators 利用推理模型作为过程评估器，提升评估阶段的计算规模 chain-of-thought
18 SemEval-2025 Task 9: The Food Hazard Detection Challenge SemEval-2025 Task 9提出基于长尾分布的食品危害检测挑战，并验证了合成数据和多种模型架构的有效性。 large language model
19 AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation AdaptiVocab：通过轻量级词汇表适配提升LLM在特定领域的效率 large language model
20 Exploring Cultural Nuances in Emotion Perception Across 15 African Languages 提出跨语言情感表达分析以解决非洲语言情感检测问题 multimodal
21 Iterative Hypothesis Generation for Scientific Discovery with Monte Carlo Nash Equilibrium Self-Refining Trees 提出MC-NEST框架，通过蒙特卡洛树搜索和纳什均衡迭代优化科学假设生成。 large language model
22 MARS: Memory-Enhanced Agents with Reflective Self-improvement MARS：提出一种记忆增强的智能体框架，通过反思性自提升解决LLM在动态环境中长期记忆和决策问题。 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🔗⭐
23 Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages 利用对比学习和大型语言模型实现跨语言零样本情感识别 contrastive learning large language model
24 Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching 提出一种基于近似似然匹配的通用跨分词器蒸馏方法，扩展LLM蒸馏的应用范围。 teacher-student distillation large language model
25 Gemma 3 Technical Report Gemma 3：推出多模态轻量级开放模型，支持视觉理解、长上下文和多语言 distillation multimodal instruction following
26 Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking 提出多轮思考（Multi-round Thinking）方法，通过迭代优化提升LLM推理能力。 reinforcement learning large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
27 A multitask transformer to sign language translation using motion gesture primitives 提出基于运动手势原语的多任务Transformer用于手语翻译 spatiotemporal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页