cs.CL（2026-09-15）

📊 共 17 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment 探讨人口统计信号对大语言模型学生评估的影响 large language model
2 Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation 利用大型语言模型提升医疗文本的可读性 large language model
3 Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning 提出Cascade框架以解决大语言模型的去学习问题 large language model
4 Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models 提出日本中风LLM评估以提升安全中风护理 large language model
5 Quantifying Organizational Environmental Action from Web Data and Large Language Models 提出一种框架以量化组织环境行动，解决信息分散问题 large language model
6 Challenges of Auditing: Variability in Outputs of Large Language Models for Health 揭示大型语言模型在健康领域审计中的输出变异性问题 large language model
7 When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control 提出Chain-of-Self-Questioning以实现选择性风险控制 large language model chain-of-thought
8 Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling 提出早鸟解码框架以加速扩散大语言模型推理 large language model
9 Where Should a Document Live: Context, Representations, or Parameters? 提出文档注入方法以提升大语言模型的知识获取能力 large language model
10 What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity 系统评估剪枝对智能家居工具调用的影响 large language model
11 Zero-shot narrative detection in social messaging 提出零样本叙事检测方法以解决社交信息中的叙事识别问题 large language model
12 RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation 提出RiskChainBench以解决平台信息恢复与网络调查问题 multimodal
13 A Data-free Universal Prior over Syntactic Structures 提出一种无数据的通用先验以理解句法结构 large language model
14 PunGraph: Retrieval-Enhanced Phonetic-Semantic Graph Reasoning for Pun Understanding 提出PunGraph以解决双关语理解中的推理问题 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🔗⭐
15 Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data 提出Style-Debiased DPO以提高LLM知识更新的准确性 DPO direct preference optimization large language model
16 TIAO: Token Importance-Aware Policy Optimization for Text Summarization 提出TIAO以解决文本摘要中的令牌重要性问题 reinforcement learning large language model foundation model ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh's July Uprising 提出UNRESTSENT200K数据集以解决孟加拉危机情感分析问题 PULSE ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页