cs.CL（2026-09-10）

📊 共 23 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) (20) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models 提出OmniHallu以解决多模态大语言模型中的幻觉检测问题 large language model multimodal
2 MultiHuSE: A Multimodal Dataset for Humour Styles and Emotions 提出MultiHuSE数据集以解决幽默风格与情感识别问题 multimodal
3 Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Completeness based Reconstruction 提出基于语义感知完整性的重建方法以解决多模态情感分析中的不完整性问题 multimodal
4 SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations 提出SWRouter以解决多轮对话中的信息路由问题 large language model
5 On the Impact of Anonymization on the Performance of Large Language Models 研究匿名化对大型语言模型性能的影响 large language model
6 Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models 提出漏斗审计方法以解决心血管筛查模型准确性问题 foundation model
7 The widening evaluation gap in medical large language model research 2023 to 2026 揭示医疗大语言模型研究中的评估差距问题 large language model
8 ReGround: Grounding Reviewer Comments in Multimodal Evidence 提出ReGround以解决评论与证据关联问题 multimodal
9 TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs 提出TransClean基准以解决LLM翻译输出中的噪声问题 large language model
10 The Illusion of Balanced Multimodal Sentiment Analysis: Beyond the Limits of Optimization-Based Methods 提出统一评估框架以解决多模态情感分析中的模态不平衡问题 multimodal
11 Distribution-aware Language Neuron Identification in Multilingual Large Language Models 提出分布感知语言神经元识别方法以提升多语言模型性能 large language model
12 Xiaomi-CocktailASR-1 Technical Report 提出Xiaomi-CocktailASR-1以解决多说话者场景下的ASR问题 large language model chain-of-thought
13 When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text 揭示噪声对大语言模型偏见测量的影响 large language model
14 Rebalancing Token Importance in Language Models with TF-IDF Weighted Cross-Entropy Loss 提出TF-IDF加权交叉熵损失以解决语言模型记忆问题 large language model
15 Recognizing Is Not Reversing: A Controlled Inversion Test of Fact-Preserving News Framing 提出控制反转测试以评估事实保留的新闻框架 large language model
16 SpecGuard: Inference-Time Backdoor Detection For Free 提出SpecGuard以解决推理时后门检测问题 large language model
17 Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs 提出组件感知差分隐私以解决联邦多语言语音LLMs问题 large language model
18 RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety 提出RAG-Safety-Bench以评估检索增强LLM的安全性问题 large language model
19 Structured Transforms for Low-Overhead Quantization of Language Models 提出改进的Kashin分解算法以优化语言模型的量化 large language model
20 Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers 提出AgentActionBench以解决科学论文实验重现性问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
21 Domain-Specific Hallucination Detection in Large Language Models 提出多信号检测管道以解决大语言模型的幻觉问题 DPO direct preference optimization large language model ✅
22 Negative Self-Distillation: Learning to Reason by Avoiding Flaws 提出负自蒸馏方法以解决复杂推理任务中的性能下降问题 reinforcement learning distillation privileged information
23 LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation 提出LOCUS以解决语言生成中的输出序列长度问题 RLHF DPO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页