cs.CL（2025-11-14）

📊 共 31 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) (25 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (25 篇)

#题目一句话要点标签🔗⭐
1 A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge 通过参数知识视角分析大语言模型中的负偏见，揭示其内在影响因素。 large language model chain-of-thought
2 Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions 提出多模态同行评审模拟系统以提升论文修订质量 large language model multimodal
3 Additive Large Language Models for Semi-Structured Text 提出CALM框架，解决LLM在半结构化临床文本分类中的可解释性问题。 large language model
4 Automata-Based Steering of Large Language Models for Diverse Structured Generation 提出基于自动机的LLM引导方法，提升结构化生成任务的多样性 large language model
5 Scaling Open-Weight Large Language Models for Hydropower Regulatory Information Extraction: A Systematic Analysis 针对水力发电监管信息抽取，系统分析了开放权重大型语言模型的性能与资源消耗。 large language model
6 Prompt-Based Value Steering of Large Language Models 提出一种基于Prompt的大语言模型价值观引导方法，无需模型微调。 large language model
7 Evaluating Large Language Models on Rare Disease Diagnosis: A Case Study using House M.D 利用《豪斯医生》数据集评估大型语言模型在罕见病诊断中的能力 large language model
8 Random Text, Zipf's Law, Critical Length,and Implications for Large Language Models 提出基于随机文本模型的Zipf定律解释，为语言模型统计特性提供零模型。 large language model
9 LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models LaoBench：首个大规模多维度老挝语基准评测，用于评估大语言模型的理解与推理能力 large language model
10 From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models 揭示工具增强语言模型中的工具诱导推理短视问题 large language model ✅
11 Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion 提出MemoDetector，通过多层次模态增强和双阶段融合提升Meme情感理解。 large language model multimodal ✅
12 Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering 提出Expert-CoT和ExpertRAG，解决急救医学问答中领域知识不足的问题 large language model chain-of-thought
13 Can LLMs Detect Their Own Hallucinations? 提出基于CoT的框架，评估LLM自检幻觉能力，提升幻觉检测准确率 large language model chain-of-thought
14 AV-Dialog: Spoken Dialogue Models with Audio-Visual Input AV-Dialog：提出一种利用音视频输入的多模态对话框架，提升噪声环境下的对话质量。 multimodal
15 Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization 提出实体匿名化方法，提升LLM在对话生成任务中对外部知识的利用率 large language model
16 InData: Towards Secure Multi-Step, Tool-Based Data Analysis InData：面向安全的多步骤、基于工具的数据分析数据集与基准 large language model
17 PRSM: A Measure to Evaluate CLIP's Robustness Against Paraphrases 提出PRSM指标，评估CLIP模型在释义变换下的鲁棒性，揭示潜在偏见。 multimodal
18 Towards Autoformalization of LLM-generated Outputs for Requirement Verification 利用LLM自动形式化LLM生成内容，用于需求验证 large language model
19 M-DAIGT: A Shared Task on Multi-Domain Detection of AI-Generated Text M-DAIGT：多领域AI生成文本检测共享任务与大规模基准数据集 large language model
20 Structured Definitions and Segmentations for Legal Reasoning in LLMs: A Study on Indian Legal Data 通过结构化定义和分割提升LLM在印度法律推理任务中的表现 large language model
21 KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement KGQuest：提出一种基于知识图谱和LLM优化的模板驱动QA生成方法 large language model
22 Automated Analysis of Learning Outcomes and Exam Questions Based on Bloom's Taxonomy 基于Bloom分类法的考试题目与学习成果自动分析方法研究 large language model
23 Community-Aligned Behavior Under Uncertainty: Evidence of Epistemic Stance Transfer in LLMs 提出一种框架，用于评估LLM在不确定性下是否表现出与特定社区一致的行为模式。 large language model
24 Analysing Personal Attacks in U.S. Presidential Debates 提出基于Transformer的框架，用于分析美国总统辩论中的人身攻击。 large language model
25 PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation PIRA：提出双重聚合的偏好导向指令微调奖励模型 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
26 W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search 提出W2S-AlignTree，通过蒙特卡洛树搜索实现大语言模型推理时对齐。 reinforcement learning RLHF large language model
27 When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets 系统性分析并优化偏好优化数据集，提升LLM对齐效果 reinforcement learning DPO direct preference optimization
28 Context-Emotion Aware Therapeutic Dialogue Generation: A Multi-component Reinforcement Learning Approach to Language Models for Mental Health Support 提出上下文-情感感知的治疗性对话生成方法，利用多组件强化学习提升语言模型在心理健康支持中的表现。 reinforcement learning large language model
29 ICX360: In-Context eXplainability 360 Toolkit ICX360：用于大语言模型上下文可解释性的开源工具包 predictive model large language model ✅
30 LANE: Lexical Adversarial Negative Examples for Word Sense Disambiguation 提出LANE对抗训练策略，通过词汇对抗负例提升词义消歧性能。 representation learning contrastive learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
31 Proactive Hearing Assistants that Isolate Egocentric Conversations 提出一种主动式助听设备，无需提示即可隔离佩戴者对话对象 egocentric

⬅️ 返回 cs.CL 首页 · 🏠 返回主页