cs.CL（2025-08-03）

📊 共 15 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 A comprehensive taxonomy of hallucinations in Large Language Models 提出全面分类法以解决大型语言模型的幻觉问题 large language model multimodal
2 Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models 提出反事实探测方法以解决大型语言模型的幻觉问题 large language model
3 MLP Memory: A Retriever-Pretrained Memory for Large Language Models 提出MLP Memory以解决大语言模型知识获取效率问题 large language model
4 Am I Blue or Is My Hobby Counting Teardrops? Expression Leakage in Large Language Models as a Symptom of Irrelevancy Disruption 提出表达泄漏概念以解决大语言模型的无关信息干扰问题 large language model
5 Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe 提出Voxlect基准以解决方言和区域语言建模问题 foundation model ✅
6 Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models 提出PromptAnatomy框架以解决提示组件对抗鲁棒性评估问题 large language model ✅
7 Web-CogReasoner: Towards Knowledge-Induced Cognitive Reasoning for Web Agents 提出Web-CogReasoner以解决网络代理的认知推理问题 multimodal chain-of-thought ✅
8 The Art of Breaking Words: Rethinking Multilingual Tokenizer Design 提出一种新算法以优化多语言分词器设计 large language model
9 Enhancing the Preference Extractor in Multi-turn Dialogues: From Annotating Disasters to Accurate Preference Extraction 提出IterChat框架以解决多轮对话中的偏好提取问题 large language model
10 CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy 提出CoCoA框架以增强参数化与检索知识的协同作用 large language model
11 The Bidirectional Process Reward Model 提出双向过程奖励模型以提升大语言模型推理质量 large language model
12 CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions 提出CUPID基准以解决LLMs个性化与上下文对齐问题 large language model
13 Authorship Attribution in Multilingual Machine-Generated Texts 提出多语言作者归属方法以解决机器生成文本识别问题 large language model
14 ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings 提出ChEmbed以解决化学文献检索中的嵌入表示不足问题 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🔗⭐
15 Word Overuse and Alignment in Large Language Models: The Influence of Learning from Human Feedback 提出一种方法以揭示大语言模型的词汇过度使用问题 reinforcement learning direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页