cs.CL（2026-09-23）

📊 共 16 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) (13 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following	提出针对翻译的LLM微调方法以解决遗忘问题	large language model instruction following
2	Beyond Poetry: Can Large Language Models Generate Classical Arabic Maqamat?	首次评估大型语言模型生成经典阿拉伯maqama的能力	large language model
3	When Context Misleads: In-context Learning with Jurisdiction in Large Language Models	提出J-ICL以解决上下文权威性不足问题	large language model	✅
4	Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models	提出RoPA管理器以自动化处理活动记录提取	large language model
5	Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents	提出WebMRE基准以研究多模态网络代理中的引导-动作相互强化问题	multimodal
6	Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models	提出Uncheatable Eval以解决语言模型评估数据污染问题	large language model instruction following	✅
7	Evaluating Feedback Focus and Pedagogical Adaptivity in LLM-Generated Feedback on Student Writing	提出FeedType以评估LLM生成反馈的教学适应性	large language model
8	Controlled Attribute-Specific Summarization of Interrogative Dialogues	提出CASPER框架以解决审问对话的特定属性摘要问题	chain-of-thought
9	Complementary Roles of Activation and Parametric Memory in Few-Shot Learning	探讨激活记忆与参数记忆在少样本学习中的互补作用	large language model
10	Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs	提出固定预算修订协议以评估LLM中的闭环修订问题	large language model	✅
11	How Much Were You Told? Measuring External Information in Peer Reviews	提出自条件化方法以测量同行评审中的外部信息	large language model
12	Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research	提出合成研究验证框架以解决行为后果与公平性问题	large language model
13	PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language Models	提出PRISM-VLM以解决紧凑型视觉语言模型评估不足问题	multimodal

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

#	题目	一句话要点	标签	🔗	⭐
14	Agent-Editing World Model: Rethinking World Modeling for LLM Agents	提出Agent-Editing世界模型以解决任务状态污染问题	world model world models large language model
15	Contrastive Learning for Authorship Verification	提出对比学习方法以提升作者验证准确性	contrastive learning
16	SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving	提出SkillGym框架以将人类技能内化为大语言模型的能力	reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页