cs.CL（2026-11-02）

📊 共 22 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models 提出PGuard以解决多模态大语言模型生成过程中的安全监控问题 large language model multimodal
2 Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks 提出能效与准确性权衡方法以优化医疗问答模型 large language model
3 Solver-Like Behavior in Large Language Models as Formalizers 提出LLM作为形式化工具以优化求解过程 large language model
4 Every Clause Counts: Instruction-Following Reranking by Multiplying Small, Answerable Questions 提出DMReranker以提升指令遵循的搜索结果排序 instruction following
5 MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages 提出MultiInpaintCOCO以解决多语言视觉理解问题 large language model multimodal ✅
6 VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations 提出VIAS以解决组织价值合规性问题 large language model
7 An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification 提出保守融合规则以优化科学声明验证 large language model
8 VERS: Steering Reasoning Models by Editing Their Activation Explanations 提出VERS以引导推理模型的激活解释 chain-of-thought
9 Tracing the Scientific Discovery Capacity of LLMs to Their Training Data 通过单一事实率提升大语言模型的科学发现能力 large language model
10 PlagiaCorpus: A Bilingual, Adversarial, and Cross-Lingual Dataset for Forensic Plagiarism Detection 提出PlagiaCorpus数据集以解决跨语言抄袭检测问题 large language model
11 They Know Where It Is, But Not What It Says: A Bilingual Hallucination Benchmark of Hadith Recall in Open LLMs 提出双语基准以评估开放语言模型在哈迪斯回忆中的表现 large language model ✅
12 Beyond Accuracy: How Quantization Affects Coding Agents 探讨量化对编码智能体行为的影响 large language model
13 VeriHarm-Bench: Measuring Harmful Success in LLM Coding Agents Verifiably 提出VeriHarm框架以可验证地衡量LLM编码代理的有害成功 large language model
14 Specificity Bias and the Wikipedia Paradox: An xAI Analysis of AI Text Detectors under Domain Shift 提出基于xAI的检测框架以解决AI文本检测的特定性偏差问题 large language model
15 DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction 提出DepthGraft以解决深层信息稀释问题 large language model ✅
16 Omni-Life: Benchmarking Omnimodal Real-Time AI Assistants in People's Daily Lives 提出Omni-Life基准以解决实时多模态助手的有效性问题 instruction following
17 LLMs Cannot Be Neutral: Gender Sensitivity Across Candidates, Evaluators, and Models 探讨性别敏感性对大型语言模型评估的影响 large language model
18 From Language to Country to Valence: A Multilingual Audit of Stereotype Bias Across LLMs 提出多语言审计方法以检测大型语言模型中的刻板印象偏见 large language model
19 As Expected? Efficient LLM Planning via Expectation-Observation Consistency Verification 提出期望-观察一致性验证机制以提高LLM规划效率 multimodal
20 InteractionBench: Measuring Timing, Task Accuracy, Whisper and Volume, and Grounding in Real-Time Voice Systems 提出InteractionBench以综合评估实时语音系统的多维性能 instruction following
21 EviCast: Forecasting Retrieval Gains Through Shared Response Calibration 提出EviCast框架以优化检索增强生成模型的性能 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
22 Meet Students Where They Are: Student-Prefix Teacher Adaptation for On-Policy Distillation 提出学生前缀教师适应以解决在政策蒸馏中的分布不匹配问题 reinforcement learning distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页