cs.CL（2025-07-30）

📊 共 31 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual-Language Models through Procedural Plans ISO-Bench：通过程序化流程基准测试视觉-语言模型中的多模态因果推理 multimodal chain-of-thought
2 Traits Run Deep: Enhancing Personality Assessment via Psychology-Guided LLM Representations and Multimodal Apparent Behaviors 提出Traits Run Deep框架，利用心理学指导的LLM表征和多模态行为增强性格评估。 large language model multimodal ✅
3 Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition 提出基于概念瓶颈模型的仇恨和反仇恨言论识别方法，提升透明性和性能。 large language model
4 BALSAM: A Platform for Benchmarking Arabic Large Language Models BALSAM：一个用于评估阿拉伯语大型语言模型的综合基准平台 large language model
5 CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records CliCARE：将大型语言模型与临床指南相结合，为纵向癌症电子病历提供决策支持 large language model
6 What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models 通过微调输入编码，提升大语言模型在抽象推理任务上的性能 large language model
7 NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models 提出NeedleChain基准，评估大语言模型在全相关上下文中的信息整合能力 large language model
8 Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning 提出一种资源高效的LLM文本嵌入自适应方法，结合Prompt工程和对比微调。 large language model
9 Listening to the Unspoken: Exploring "365" Aspects of Multimodal Interview Performance Assessment 提出融合多模态信息的面试表现评估框架，提升评估的全面性和公平性。 multimodal ✅
10 Multilingual Political Views of Large Language Models: Identification and Steering 大规模研究揭示LLM多语言政治倾向并提出干预方法 large language model ✅
11 A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support 提出CSConDa数据集与评测框架，用于评估越南语大模型在客服场景下的性能 large language model ✅
12 PATENTWRITER: A Benchmarking Study for Patent Drafting with LLMs PATENTWRITER：利用LLM进行专利撰写基准测试，提升专利申请效率 large language model chain-of-thought
13 IFEvalCode: Controlled Code Generation 提出IFEvalCode基准，通过前后约束生成提升代码大模型指令遵循能力 large language model instruction following
14 RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL RASL：提出检索增强的模式链接方法，解决大规模数据库Text-to-SQL的挑战。 large language model
15 Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity 揭示大语言模型在处理中文文本歧义时的脆弱性 large language model ✅
16 C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations C3：双语口语对话模型基准，探索复杂对话中的挑战 large language model
17 Exploring In-Context Learning for Frame-Semantic Parsing 探索上下文学习用于框架语义分析，无需微调实现高性能 large language model
18 Opportunities and Challenges of LLMs in Education: An NLP Perspective 探讨LLM在教育领域的机遇与挑战，聚焦NLP视角下的辅助与评估两大应用场景。 large language model
19 Investigating Hallucination in Conversations for Low Resource Languages 针对低资源语言对话场景，研究大型语言模型中的幻觉问题 large language model
20 Heartificial Intelligence: Exploring Empathy in Language Models 评估语言模型共情能力：大型模型认知共情超越人类，但情感共情仍有差距 large language model
21 WINELL: Wikipedia Never-Ending Updating with LLM Agents WiNELL：利用LLM Agent持续更新维基百科知识 instruction following
22 PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins PersonaTwin：多层提示调节框架，用于生成和评估个性化数字孪生 large language model
23 Hierarchical Verification of Speculative Beams for Accelerating LLM Inference 提出分层验证树(HVT)加速LLM推断，提升推断效率和降低能耗。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
24 TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning TT-XAI：通过关键词提炼与LLM推理，提升临床文本解释的可信度 distillation large language model chain-of-thought
25 Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance Falcon-H1：混合头语言模型系列，重新定义效率与性能的平衡 Mamba SSM state space model
26 Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index 提出基于强化学习和实体幻觉指标的摘要生成方法，减少摘要中的幻觉问题。 reinforcement learning
27 From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs TIRESRAG-R1：通过强化学习引导检索增强推理，提升LLM的推理质量 reinforcement learning large language model ✅
28 SLM-SQL: An Exploration of Small Language Models for Text-to-SQL 提出SLM-SQL，探索小语言模型在Text-to-SQL任务中的潜力，并显著提升其性能。 reinforcement learning large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
29 Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation 提出语言算术方法，系统性识别和操控LLM中的语言神经元 manipulation large language model ✅
30 Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs 提出CognitiveAttack，利用认知偏差组合绕过大型语言模型安全机制 manipulation reinforcement learning large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
31 GeoOutageKG: A Multimodal Geospatiotemporal Knowledge Graph for Multiresolution Power Outage Analysis 提出GeoOutageKG，用于多分辨率电力中断分析的多模态地理时空知识图谱 spatiotemporal multimodal

⬅️ 返回 cs.CL 首页 · 🏠 返回主页