cs.CL（2025-01-02）

📊 共 23 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) (21 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

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

#题目一句话要点标签🔗⭐
1 ProgCo: Program Helps Self-Correction of Large Language Models ProgCo：利用程序辅助大语言模型进行自我纠错，提升复杂推理能力 large language model instruction following ✅
2 Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models 构建Singlish理解桥梁：发布数据集与多模态模型SingAudioLLM large language model multimodal
3 Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs SafeNudge：一种可调安全-性能权衡的LLM实时安全防护方法 large language model
4 Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts 提出线性变换方法，实现大语言模型间概念表示的跨模型迁移与行为控制。 large language model
5 Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case 探索大语言模型辅助精神健康诊断评估：以抑郁症和焦虑症为例 large language model
6 Does a Large Language Model Really Speak in Human-Like Language? 提出统计假设检验框架以比较LLM与人类文本的相似性 large language model
7 Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion 提出LLM增强的符号推理框架，用于提升知识库补全的灵活性和可靠性 large language model
8 Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models 提出动态注意力引导的上下文解码DAGCD，缓解大语言模型中的上下文忠实性幻觉问题 large language model
9 Risks of Cultural Erasure in Large Language Models 评估大型语言模型中文化抹除风险，关注遗漏与简化两种形式 large language model
10 MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model MDSF：基于大语言模型的上下文感知多维数据故事讲述框架 large language model
11 Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory 基于信息瓶颈理论探索大语言模型的信息处理机制，并提出IC-ICL和TS-FT方法。 large language model
12 Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection 提出基于语义图增强不确定性建模的幻觉检测方法 large language model
13 OmniChat: Enhancing Spoken Dialogue Systems with Scalable Synthetic Data for Diverse Scenarios OmniChat：利用可扩展的合成数据增强口语对话系统，覆盖多样化场景 large language model
14 Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking 提出HaluSearch框架，通过快慢双重思维过程缓解大语言模型的幻觉问题 large language model
15 CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings CodeElo：提出基于Elo等级分的LLM代码生成能力竞赛级评测基准 large language model
16 Self-Refinement Strategies for LLM-based Product Attribute Value Extraction 研究表明，基于LLM的自精炼策略在产品属性值抽取任务中未能有效提升性能。 large language model
17 BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference BlockDialect：面向节能LLM推理的块状细粒度混合格式量化 large language model
18 Dynamic Scaling of Unit Tests for Code Reward Modeling 提出CodeRM-8B，通过动态调整单元测试规模提升代码奖励建模性能 large language model
19 FED: Fast and Efficient Dataset Deduplication Framework with GPU Acceleration FED：基于GPU加速的高效数据集去重框架，提升LLM训练效率 large language model ✅
20 ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning 提出ValuesRAG，通过检索增强上下文学习提升LLM的跨文化价值观对齐能力 large language model
21 KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model KaLM-Embedding：通过高质量训练数据提升通用多语言嵌入模型性能 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
22 Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension 提出K-(CSA)^2框架以深入理解大型语言模型的知识结构 reinforcement learning large language model chain-of-thought
23 Aligning Large Language Models for Faithful Integrity Against Opposing Argument 提出AFICE框架，提升大语言模型在对抗性论证下的忠实性和可靠性 DPO direct preference optimization large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页