cs.CL（2026-03-24）

📊 共 20 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) (18 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature	提出HGNet，用于从科学文献中自动生成可扩展的知识图谱。	large language model foundation model	✅
2	I Came, I Saw, I Explained: Benchmarking Multimodal LLMs on Figurative Meaning in Memes	评估多模态大语言模型在理解表情包中隐喻含义的能力，揭示其在多模态推理上的局限性。	large language model multimodal
3	Is AI Catching Up to Human Expression? Exploring Emotion, Personality, Authorship, and Linguistic Style in English and Arabic with Six Large Language Models	评估大型语言模型在英语和阿拉伯语中模仿人类情感、个性和写作风格的能力	large language model
4	Failure of contextual invariance in gender inference with large language models	揭示大语言模型在性别推断中违反上下文不变性，挑战现有评估标准。	large language model
5	Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees	提出可行性感知覆盖保证的LLM集合值预测框架，提升生成质量	large language model
6	Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation	提出区分不文明和不容忍言论的多模态内容审核方案，提升审核准确性和可靠性。	multimodal
7	Decoding AI Authorship: Can LLMs Truly Mimic Human Style Across Literature and Politics?	评估大型语言模型模仿人类写作风格的能力，揭示AI生成文本与人类写作的差异。	large language model
8	Improving LLM Predictions via Inter-Layer Structural Encoders	提出Inter-Layer Structural Encoders (ILSE)以提升LLM在分类和语义相似性任务中的预测性能。	large language model
9	Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy	提出基于可解释AI的框架，揭示AI生成文本检测器在跨域泛化上的缺陷	large language model
10	DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Persona	DALDALL：利用LLM-Persona增强法律领域词汇和语义多样性的数据增强方法	large language model
11	When Language Models Lose Their Mind: The Consequences of Brain Misalignment	研究表明：大脑对齐对语言模型的语言能力至关重要	large language model
12	Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy	提出TeDA框架，用于校准本地差分隐私下文本重写机制的经验隐私损失。	large language model
13	EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction	EchoKV：基于相似性重建的高效KV缓存压缩方案，提升长文本LLM性能。	large language model
14	The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration	综述LLM Agent工具使用演进：从单工具调用到多工具编排	large language model
15	Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts	分析LLM在极化地缘政治背景下的人格生成与公平性解释	large language model
16	Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration	提出自适应贝叶斯估计框架，高效检测大语言模型中的幻觉问题	large language model
17	Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Loss	提出基于Span对比损失的跨度建模方法，用于成语和比喻语言检测。	large language model
18	Detecting Non-Membership in LLM Training Data via Rank Correlations	提出PRISM，通过秩相关性检测LLM训练数据非成员性，用于版权合规审计。	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	🔗	⭐
19	Quality Over Clicks: Intrinsic Quality-Driven Iterative Reinforcement Learning for Cold-Start E-Commerce Query Suggestion	提出Cold-EQS，利用内在质量驱动的迭代强化学习解决电商冷启动查询推荐问题	reinforcement learning large language model
20	ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment	提出ImplicitRM以解决隐式偏好数据的无偏奖励建模问题	reinforcement learning RLHF

⬅️ 返回 cs.CL 首页 · 🏠 返回主页