cs.CL（2025-08-25）

📊 共 38 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) (31 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (7)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (31 篇)

#题目一句话要点标签🔗⭐
1 Principled Detection of Hallucinations in Large Language Models via Multiple Testing 通过多重检验方法检测大语言模型中的幻觉现象 large language model
2 Integrating gender inclusivity into large language models via instruction tuning 通过指令调优将性别包容性整合入大型语言模型 large language model
3 Demographic Biases and Gaps in the Perception of Sexism in Large Language Models 探讨大型语言模型中性别歧视感知的群体偏见与差距 large language model
4 Leveraging Large Language Models for Accurate Sign Language Translation in Low-Resource Scenarios 提出AulSign以解决低资源场景下的手语翻译问题 large language model
5 DiscussLLM: Teaching Large Language Models When to Speak 提出DiscussLLM以解决大语言模型的主动性不足问题 large language model
6 SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media 提出SentiMM框架以解决社交媒体情感分析中的多模态挑战 multimodal
7 How Quantization Shapes Bias in Large Language Models 评估量化对大语言模型偏见的影响 large language model
8 A Retail-Corpus for Aspect-Based Sentiment Analysis with Large Language Models 提出多语言零售评论数据集以提升基于方面的情感分析 large language model
9 Understanding Subword Compositionality of Large Language Models 提出对大语言模型子词组合性的深入理解 large language model
10 Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model 提出多层次分析方法以提升加密货币新闻分析的准确性 large language model
11 CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models 提出CoCoA以解决大型语言模型中的知识冲突问题 large language model
12 SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models 提出SurveyGen以解决科学文献自动调查生成问题 large language model
13 Steering When Necessary: Flexible Steering Large Language Models with Backtracking 提出灵活激活引导机制以解决大语言模型行为对齐问题 large language model ✅
14 Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions 提出HGLA修剪方法以提升大语言模型的公平性 large language model ✅
15 Training Language Model Agents to Find Vulnerabilities with CTF-Dojo 提出CTF-Dojo以解决可扩展执行环境不足问题 large language model
16 How Reliable are LLMs for Reasoning on the Re-ranking task? 分析不同训练方法对LLM重排序任务的影响 large language model
17 Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning 提出潜在自一致性方法以解决长短答案推理中的一致性问题 large language model
18 Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails 提出反向提示技术以生成健康建议的标注数据 large language model
19 From BERT to LLMs: Comparing and Understanding Chinese Classifier Prediction in Language Models 比较BERT与LLMs在中文分类器预测中的表现 large language model
20 Detecting and Characterizing Planning in Language Models 提出形式化标准以检测语言模型中的规划行为 large language model
21 Debiasing Multilingual LLMs in Cross-lingual Latent Space 提出跨语言潜在空间去偏见方法以提升多语言LLM性能 large language model
22 AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation 提出AMELIA以解决多任务论证挖掘问题 large language model
23 ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models 提出ILRe以解决长上下文处理中的效率问题 large language model
24 Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs 比较离散标记与连续特征在语音理解中的表现 large language model
25 Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning 提出MARK框架以提升文化价值调查模拟的准确性与可解释性 large language model
26 The ProLiFIC dataset: Leveraging LLMs to Unveil the Italian Lawmaking Process 提出ProLiFIC数据集以揭示意大利立法过程 large language model
27 ISACL: Internal State Analyzer for Copyrighted Training Data Leakage 提出ISACL以解决大型语言模型版权数据泄露问题 large language model ✅
28 SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validation 提出SMITE以解决大型语言模型公平性问题 large language model
29 How Do LLM-Generated Texts Impact Term-Based Retrieval Models? 探讨LLM生成文本对基于术语检索模型的影响 large language model
30 Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit 提出一种新方法以减少大型语言模型的过度思考问题 large language model
31 Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design 提出多层次设计框架以优化大型语言模型的人性化特征 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
32 Enhancing Speech Large Language Models through Reinforced Behavior Alignment 提出强化行为对齐框架以提升语音大语言模型性能 reinforcement learning distillation large language model
33 Weights-Rotated Preference Optimization for Large Language Models 提出权重旋转偏好优化以解决大语言模型的奖励黑客问题 DPO direct preference optimization large language model
34 Multimodal Proposal for an AI-Based Tool to Increase Cross-Assessment of Messages 提出多模态框架以增强财报会议的跨评估能力 contrastive learning multimodal
35 DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models 提出DRQA以解决推理大语言模型的过度思考问题 reinforcement learning large language model
36 EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning 提出EMPOWER框架以优化医疗领域的提示工程问题 reinforcement learning representation learning large language model
37 S2Sent: Nested Selectivity Aware Sentence Representation Learning 提出S2Sent以优化Transformer句子表示学习中的语义选择问题 representation learning contrastive learning
38 Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundaries 提出ESFP-RM模型以提升语言模型奖励建模效果 reinforcement learning RLHF

⬅️ 返回 cs.CL 首页 · 🏠 返回主页