cs.CL（2026-01-26）

📊 共 24 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) (14) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗3) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Using Large Language Models to Construct Virtual Top Managers: A Method for Organizational Research	利用大型语言模型构建虚拟高管，为组织研究提供新方法	large language model
2	Demographic Probing of Large Language Models Lacks Construct Validity	大型语言模型人口统计探测缺乏结构效度：提示词选择影响模型行为	large language model
3	Latent Knowledge as a Predictor of Fact Acquisition in Fine-Tuned Large Language Models	利用潜在知识预测微调大语言模型中的事实获取速度与泛化能力	large language model
4	Designing large language model prompts to extract scores from messy text: A shared dataset and challenge	提出一个用于评估LLM从文本中提取研究质量评分能力的数据集与挑战。	large language model
5	When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs	针对医学LLM，提出加权Adapter融合方法，解决领域预训练与指令对齐的干扰问题	large language model instruction following
6	Grounded Concreteness: Human-Like Concreteness Sensitivity in Vision-Language Models	研究视觉语言模型对具体概念的敏感性，揭示其更接近人类的理解能力。	large language model multimodal
7	One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment	提出元奖励建模(MRM)框架，解决个性化LLM对齐中用户反馈稀疏和泛化难题。	large language model
8	Calibrating Beyond English: Language Diversity for Better Quantized Multilingual LLM	提出多语言校准方法，提升量化多语言大语言模型在多种语言上的性能。	large language model
9	MortalMATH: Evaluating the Conflict Between Reasoning Objectives and Emergency Contexts	MortalMATH：评估推理目标与紧急情境下的冲突	large language model
10	Hierarchical Text Classification with LLM-Refined Taxonomies	提出TaxMorph框架以优化层次文本分类中的模糊分类问题	large language model
11	U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents	U-Fold：面向用户中心代理的动态意图感知上下文折叠方法	large language model
12	MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning	MemWeaver：编织混合记忆，实现可追溯的长程Agent推理	large language model
13	FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning	FABLE：提出一种基于森林结构的自适应双路径LLM增强检索框架，用于多文档推理。	large language model
14	Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents	利用大型语言模型进行合作推理：作为花火战略智能体	instruction following

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
15	Integrating Fine-Grained Audio-Visual Evidence for Robust Multimodal Emotion Reasoning	提出SABER-LLM框架，通过细粒度音视频证据融合提升多模态情感推理的鲁棒性。	direct preference optimization large language model multimodal	✅
16	Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models	Typhoon-S：面向主权大语言模型的极简开放式后训练方法	distillation large language model
17	OCR-Enhanced Multimodal ASR Can Read While Listening	提出Donut-Whisper模型，利用视觉信息提升多语种语音识别性能	distillation multimodal
18	Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale	提出Reflect，一种无需训练的原则引导推理框架，提升LLM的宪法对齐能力。	reinforcement learning RLHF large language model
19	Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning	提出Temp-R1以解决复杂时间知识图谱问答问题	reinforcement learning curriculum learning	✅
20	Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning	提出SP3F框架，利用特权信息提升大语言模型在目标语言上的推理能力	privileged information large language model
21	From Classification to Ranking: Enhancing LLM Reasoning Capabilities for MBTI Personality Detection	提出基于排序的强化学习方法，提升LLM在MBTI性格检测中的推理能力	reinforcement learning large language model
22	From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation	提出基于可验证参考奖励的强化学习(RLVRR)，用于开放式生成的LLM对齐。	reinforcement learning	✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs	提出LLM细粒度多概念控制评估框架，揭示模型在组合性上的局限性	HuMoR large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
24	Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection	揭示LLM中隐藏意图的检测困境，提出分类体系并分析检测方法失效的原因	manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页