cs.CL（2026-02-18）

📊 共 17 篇论文

🎯 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) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 IndicEval: A Bilingual Indian Educational Evaluation Framework for Large Language Models IndicEval：一个双语印度教育评估框架，用于评估大型语言模型 large language model chain-of-thought
2 Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications 构建长尾知识分析框架，提升大语言模型在低频知识上的表现 large language model
3 Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens 提出SODA：通过交错语义、声学和文本token扩展开放离散音频基础模型 foundation model
4 AREG: Adversarial Resource Extraction Game for Evaluating Persuasion and Resistance in Large Language Models 提出AREG以评估大语言模型的说服力与抵抗力 large language model
5 Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment 提出多语言一致性损失(MLC)，提升LLM在多语言环境下的安全性对齐。 large language model
6 Who can we trust? LLM-as-a-jury for Comparative Assessment 提出BT-sigma模型，通过LLM陪审团进行无监督校准的NLG评估 large language model
7 Learning to Learn from Language Feedback with Social Meta-Learning 提出基于社会元学习的语言反馈学习方法，提升LLM对话交互能力 large language model
8 Quecto-V1: Empirical Analysis of 8-bit Quantized Small Language Models for On-Device Legal Retrieval Quecto-V1：面向设备端法律检索的8比特量化小型语言模型实证分析 large language model
9 CitiLink-Summ: Summarization of Discussion Subjects in European Portuguese Municipal Meeting Minutes CitiLink-Summ：提出欧洲葡萄牙语市政会议记录讨论主题的自动摘要数据集与基线方法 large language model
10 TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifiers TabAgent框架用表格文本分类器替换Agentic系统中生成式组件，显著降低延迟和成本。 large language model
11 MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models 提出MultiCW大规模多语言平衡基准数据集，用于训练鲁棒的Check-Worthiness检测模型 large language model
12 Aladdin-FTI @ AMIYA Three Wishes for Arabic NLP: Fidelity, Diglossia, and Multidialectal Generation Aladdin-FTI模型：解决阿拉伯语NLP中方言建模难题，支持多方言生成与翻译 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis 提出Missing-by-Design框架，实现可撤销的多模态情感分析，保障用户隐私。 representation learning multimodal
14 Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution 提出REMUL，通过多方监听软执行提升LLM推理的忠实性和性能 reinforcement learning large language model chain-of-thought
15 Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection 提出Emotion Collider，利用双曲超图反射机制进行情感恢复，提升多模态情感理解的鲁棒性。 contrastive learning multimodal
16 Supercharging Agenda Setting Research: The ParlaCAP Dataset of 28 European Parliaments and a Scalable Multilingual LLM-Based Classification 提出ParlaCAP数据集和基于LLM的多语种议题分类方法，用于欧洲议会政治议程分析。 teacher-student large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
17 Optimizing Soft Prompt Tuning via Structural Evolution 提出基于结构演化的软提示优化方法，提升大语言模型微调性能。 implicit representation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页