cs.CL（2025-04-29）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption	提出Chain-of-Defensive-Thought，提升大语言模型在参考信息污染下的鲁棒性	large language model chain-of-thought
2	LLM Enhancer: Merged Approach using Vector Embedding for Reducing Large Language Model Hallucinations with External Knowledge	LLM Enhancer：融合向量嵌入与外部知识，减少大语言模型幻觉	large language model
3	Improving Phishing Email Detection Performance of Small Large Language Models	提出Prompt工程、解释增强微调和模型集成方法，提升小型LLM在钓鱼邮件检测中的性能。	large language model
4	Information Gravity: A Field-Theoretic Model for Token Selection in Large Language Models	提出信息引力模型，用场论解释大语言模型中的token选择过程	large language model
5	A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies	评估大型语言模型聊天机器人对民主社会构成的说服风险框架	large language model
6	Computational Reasoning of Large Language Models	提出Turing Machine Bench，评估LLM在规则遵循和状态管理方面的计算推理能力	large language model	✅
7	WenyanGPT: A Large Language Model for Classical Chinese Tasks	WenyanGPT：面向古文任务的大语言模型，性能显著超越现有模型	large language model
8	Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models	利用大型语言模型实现零样本实体框架分类，提升新闻叙事理解	large language model
9	Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think	提出基于子思想聚合的LLM推理方法，提升复杂数学问题求解精度	large language model	✅
10	TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models	提出TF1-EN-3M：一个用于训练小型开放语言模型的包含三百万条合成道德寓言的数据集。	instruction following
11	Automatic Legal Writing Evaluation of LLMs	提出oab-bench：用于自动评估LLM法律写作能力的新基准	large language model
12	OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification	OSVBench：用于操作系统验证的LLM规范生成基准测试	large language model	✅
13	HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation	HyPerAlign：通过假设生成实现可解释的个性化LLM对齐	large language model
14	A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages	提出基于生成式AI的声明检索系统，用于多语言社交媒体平台的事实核查。	large language model
15	BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters	BrAIcht：一种模仿布莱希特戏剧风格的AI对话代理	large language model
16	Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training	提出CrossIC-PT，通过跨语言上下文预训练增强LLM的语言适应能力	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
17	UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation	UniDetox：通过数据集蒸馏实现大型语言模型的通用解毒	distillation large language model
18	Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition	提出Trace-of-Thought Prompting，用于低资源模型知识蒸馏，提升推理能力。	distillation large language model
19	DYNAMAX: Dynamic computing for Transformers and Mamba based architectures	提出DYNAMAX以提升Mamba架构的早期退出机制	Mamba

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination	通过结构化重组提升LLM创造力以解决创意不足问题	manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页