cs.CL（2026-03-26）

📊 共 17 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) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models	大型语言模型指令拓扑受社会语域影响：命令式干预研究	large language model instruction following
2	Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers	分析大型语言模型对学术论文的影响，揭示词汇使用模式的转变。	large language model
3	Closing the Confidence-Faithfulness Gap in Large Language Models	提出自适应steering方法，弥合大语言模型置信度与准确率之间的差距	large language model
4	Self-Improvement of Large Language Models: A Technical Overview and Future Outlook	提出自提升LLM统一框架，通过闭环生命周期实现模型能力迭代优化	large language model
5	Large Language Model as Token Compressor and Decompressor	提出基于LLM的自编码框架，实现文本token的高效压缩与解压缩	large language model
6	Approaches to Analysing Historical Newspapers Using LLMs	结合LLM与传统方法，分析斯洛文尼亚历史报纸的集体认同与政治倾向。	large language model instruction following
7	Measuring What Matters -- or What's Convenient?: Robustness of LLM-Based Scoring Systems to Construct-Irrelevant Factors	评估LLM评分系统对与评估目标无关因素的鲁棒性	large language model
8	CRAFT: Grounded Multi-Agent Coordination Under Partial Information	CRAFT：部分信息下基于语言的大模型多智能体协作基准	large language model	✅
9	Probing the Lack of Stable Internal Beliefs in LLMs	探究LLM缺乏稳定内部信念：在多轮对话中保持隐式目标一致性	large language model
10	PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency	PICon：多轮审讯框架，评估Persona Agent的一致性	large language model	✅
11	Humans vs Vision-Language Models: A Unified Measure of Narrative Coherence	提出统一的叙事连贯性度量方法，对比人类与视觉-语言模型在视觉故事生成中的表现。	multimodal	✅
12	Navigating the Prompt Space: Improving LLM Classification of Social Science Texts Through Prompt Engineering	通过Prompt工程优化LLM在社会科学文本分类中的性能	large language model
13	Separate Before You Compress: The WWHO Tokenization Architecture	提出WWHO分词架构，解决复杂Abugida文字Token Tax问题，提升LLM效率。	large language model
14	Comparing Natural and Synthetic Structured Data: A Study of the Passive Verb Alternation in French and Italian	比较自然与合成结构数据以研究法语和意大利语的被动动词交替	large language model
15	Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection	提出Exons-Detect以解决AI生成文本检测的鲁棒性问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning	提出TAPO：一种翻译增强策略优化方法，提升LLM在多语言数学推理中的能力。	reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory	利用信号检测理论评估LLM的元认知效率，揭示模型“知其不知”的能力差异	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页