cs.CL（2026-07-27）

📊 共 16 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting 提出StanceFlip基准以解决多模态对话立场翻转预测问题 large language model multimodal
2 D-Score: A Spectral Hidden-State Signal for Hallucination Detection in Large Language Models 提出D-Score以解决大型语言模型的幻觉检测问题 large language model
3 Understanding Tone-Dependent Inference Cost in Large Language Models 研究提示语语气对大型语言模型推理成本的影响 large language model
4 Systematic Analysis of Large Language Models and Transformer-Based Machine Translation for English-Tamil and Tamil-English Across Diverse Datasets 系统分析大型语言模型与基于变换器的机器翻译以解决泰米尔语翻译问题 large language model
5 SINT-Flow: Schema Integration using Large Language Model Workflows 提出SINT-Flow以解决模式集成问题 large language model
6 Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Management 提出基于RAG的LLM架构以提升监管知识管理的可靠性 large language model
7 INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models 提出INS-ActBench以评估大型语言模型的精算能力 large language model ✅
8 The Tokenizer Tax: Quantifying and Explaining the Cross-Lingual Cost of Subword Tokenization for Indian Languages 量化印度语言的子词标记化成本以解决跨语言问题 large language model
9 LLM-based Source Code Compression via Thresholded Symbol Ranking 提出基于LLM的源代码压缩方法以解决存储需求问题 large language model
10 DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data 提出DataOrchestra以解决预训练数据处理不适应性问题 large language model
11 LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings 提出LEX-EC框架以解决大语言模型个性分类的可解释性问题 large language model
12 SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding 提出SyRuP以增强大型语言模型对系统提示的遵循能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
13 CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models 提出CONSISTRE框架以解决文档级关系抽取中的一致性问题 reinforcement learning distillation large language model
14 The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation 提出统一控制的多回合长远规划方法以提升基础模型能力 world model world models distillation
15 Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis 提出FacialTalker以解决对话语音合成中的面部表情建模问题 DPO direct preference optimization large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 Rethinking the Generation Order of Block Diffusion Language Models 提出PARD以优化块扩散语言模型的生成顺序 MDM

⬅️ 返回 cs.CL 首页 · 🏠 返回主页