cs.CL（2025-07-17）

📊 共 19 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Automating Steering for Safe Multimodal Large Language Models 提出AutoSteer，用于安全引导多模态大语言模型推理，无需微调。 large language model multimodal
2 Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models Promptomatix：一种用于大型语言模型的自动提示优化框架 large language model
3 AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research AbGen：首个评估大语言模型在科学研究中消融实验设计能力的基准 large language model
4 A Survey of Context Engineering for Large Language Models 综述论文：针对大语言模型的上下文工程，系统性优化信息载荷以提升模型性能。 large language model
5 Enhancing Cross-task Transfer of Large Language Models via Activation Steering 提出CAST，通过激活调控实现大语言模型跨任务迁移，无需参数更新。 large language model
6 Large Language Models' Internal Perception of Symbolic Music 探索大语言模型对符号音乐的内在感知能力 large language model
7 Strategy Adaptation in Large Language Model Werewolf Agents 提出基于策略自适应的大语言模型狼人杀Agent，提升复杂博弈场景表现 large language model
8 AdaptiSent: Context-Aware Adaptive Attention for Multimodal Aspect-Based Sentiment Analysis AdaptiSent：提出上下文感知自适应注意力机制，用于多模态方面级情感分析。 multimodal
9 Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation 提出印地语类比测试集HATS，揭示多语言LLM在印地语推理能力上的不足。 large language model chain-of-thought
10 Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? 重新审视LLM价值探测策略：它们是否稳健且富有表现力？ large language model
11 Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes 构建多类型幽默理解数据集，揭示LLM在复杂幽默解释上的局限性 large language model
12 A Computational Framework to Identify Self-Aspects in Text 提出一种计算框架以识别文本中的自我方面，应用于心理健康和经验现象学研究。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
13 HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals 提出HapticCap数据集和触觉-文本检索任务，用于理解振动触觉信号的用户体验。 contrastive learning multimodal
14 CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation 提出CCL-XCoT框架，通过跨语言知识迁移缓解多语言大模型中的幻觉生成问题 contrastive learning large language model chain-of-thought
15 Logit Arithmetic Elicits Long Reasoning Capabilities Without Training 提出ThinkLogit，无需训练即可激发大模型长推理能力 reinforcement learning DPO chain-of-thought
16 Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management TalentCLEF 2025：首个面向人力资本管理的技能与职位智能评测基准 contrastive learning large language model
17 QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation QuestA：通过问题增广提升大型语言模型在推理任务中的能力 reinforcement learning large language model ✅
18 Learning Robust Negation Text Representations 提出一种基于蒸馏学习的文本编码器优化方法，提升其在否定语义理解上的鲁棒性。 contrastive 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🔗⭐
19 The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner 提出图灵机模仿学习(TAIL)，提升LLM在可计算推理任务上的长度泛化能力。 manipulation imitation learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页