cs.CL（2026-02-07）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Efficient Post-Training Pruning of Large Language Models with Statistical Correction	提出基于统计校正的高效大语言模型后训练剪枝方法	large language model
2	SciClaimEval: Cross-modal Claim Verification in Scientific Papers	SciClaimEval：提出一个科学论文中跨模态声明验证的新数据集	large language model foundation model multimodal
3	Do Large Language Models Reflect Demographic Pluralism in Safety?	Demo-SafetyBench：构建考虑人口多元性的LLM安全评估基准	large language model
4	Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification	提出基于动态路径规划的逐步简化框架，提升大语言模型在多语言无监督可控句子简化任务上的性能。	large language model chain-of-thought
5	Improving Variable-Length Generation in Diffusion Language Models via Length Regularization	提出LR-DLLM，通过长度正则化改进扩散语言模型中的变长生成问题。	large language model
6	Advantages of Domain Knowledge Injection for Legal Document Summarization: A Case Study on Summarizing Indian Court Judgments in English and Hindi	通过注入领域知识改进法律文档摘要：以英印法院判决摘要为例	large language model
7	TernaryLM: Memory-Efficient Language Modeling via Native 1-Bit Quantization with Adaptive Layer-wise Scaling	TernaryLM：通过自适应层缩放的原生1比特量化实现内存高效的语言建模。	large language model	✅
8	Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation	提出Mediator-Assistant架构，解决LLM在多轮对话中因意图不匹配导致的性能下降问题	large language model
9	Blind to the Human Touch: Overlap Bias in LLM-Based Summary Evaluation	揭示LLM摘要评估中的重叠偏差：LLM倾向于与自身相似的生成摘要	large language model
10	Letting Tutor Personas "Speak Up" for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization	提出基于偏好优化的对话转向向量学习方法，实现LLM导师角色定制	large language model
11	Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models	训练驱动的表征几何模块化预测语言模型中的大脑对齐	large language model
12	From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection	提出跨文化评估框架，提升视觉-语言模型在仇恨模因检测中的鲁棒性。	multimodal
13	DLLM Agent: See Farther, Run Faster	提出DLLM Agent，利用扩散模型提升Agent多步决策效率与规划能力。	large language model
14	When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified	AlignX：通过解耦特征空间和校准专家路由，提升LLM的HHH对齐效果	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	🔗	⭐
15	Learning to Self-Verify Makes Language Models Better Reasoners	提出自验证学习框架，提升语言模型在复杂推理任务中的性能	reinforcement learning large language model
16	SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning	SED-SFT：通过选择性鼓励多样性来提升监督式微调效果	reinforcement learning large language model	✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页