cs.CL（2026-04-28）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models 提出SOB：一个多源结构化输出基准，用于评估大语言模型在结构化数据提取中的质量。 large language model
2 LegalMidm: Use-Case-Driven Legal Domain Specialization for Korean Large Language Model LegalMidm：针对韩国法律领域，以用例驱动的大语言模型专业化 large language model
3 Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs 提出基于医学实体树的MLLM数据工程框架，提升医学领域复杂推理能力。 large language model multimodal
4 Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling Luminol-AIDetect：基于文本洗牌困惑度的快速零样本机器生成文本检测 large language model
5 CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation 比较传统方法与LLM，用于食谱营养成分估计，权衡精度与效率 large language model
6 Cross-Lingual Jailbreak Detection via Semantic Codebooks 提出基于语义编码本的跨语言越狱检测方法，无需重训练或特定语言适配。 large language model
7 LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation 提出LLM-ReSum框架，通过自评估提升LLM生成摘要的质量和准确性 large language model
8 From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation 提出依赖驱动的提示管道，用于生成具有连贯性的RPG游戏内容 large language model
9 Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment? 提出文化对齐评估数据集构建指南，提升LLM文化敏感性测试的区分度 large language model
10 FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments FAMA：面向交互式工具使用环境，基于失败感知的开源LLM元代理框架 large language model
11 What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective 提出基于加权上下文影响的指令数据选择框架，提升指令调优效果 instruction following

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

#题目一句话要点标签🔗⭐
12 Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation 提出基于回译增强的直接偏好优化方法，提升神经机器翻译质量 reinforcement learning DPO direct preference optimization
13 One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement 提出ReQueR，通过强化学习优化查询，提升大语言模型推理能力。 reinforcement learning large language model ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
14 From Syntax to Emotion: A Mechanistic Analysis of Emotion Inference in LLMs 利用稀疏自编码器和因果追踪，剖析大型语言模型中的情感推理机制 motion prediction motion representation large language model

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

#题目一句话要点标签🔗⭐
15 Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives 利用指示词揭示LLM在具身认知和文化差异理解上的不足 egocentric large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios DV-World：构建真实世界数据可视化Agent的基准测试平台 manipulation ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页