cs.CL（2025-07-11）

📊 共 29 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) (26 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 Multilingual Multimodal Software Developer for Code Generation 提出MM-Coder：一个多语言多模态软件开发者，利用视觉工作流提升代码生成。 large language model multimodal instruction following
2 Lizard: An Efficient Linearization Framework for Large Language Models Lizard：一种高效线性化框架，用于加速和优化大型语言模型 large language model
3 Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences 利用大型语言模型检测多智能体决策会议中的共识 large language model
4 Semantic Source Code Segmentation using Small and Large Language Models 提出基于大小语言模型的语义源代码分割方法，提升低资源语言代码理解。 large language model
5 LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning LLaPa：一个用于反事实感知程序规划的视觉-语言模型框架 embodied AI large language model multimodal ✅
6 Using Large Language Models for Legal Decision-Making in Austrian Value-Added Tax Law: An Experimental Study 利用大型语言模型辅助奥地利增值税法法律决策 large language model
7 Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework 提出AttriData和MisAttributionLLM，用于诊断大型语言模型回答中的错误并进行归因。 large language model
8 xpSHACL: Explainable SHACL Validation using Retrieval-Augmented Generation and Large Language Models xpSHACL：利用RAG和LLM实现可解释的SHACL验证 large language model
9 A Survey of Large Language Models in Discipline-specific Research: Challenges, Methods and Opportunities 综述性研究：分析大语言模型在跨学科研究中的挑战、方法与机遇 large language model
10 Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency 提出同步自审OCR能力（SSR）微调范式，提升MLLM文档图像机器翻译性能并缓解OCR能力遗忘。 large language model multimodal
11 A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1 对比LLAMA到GPT-4o等LLM在论证分类任务上的性能，发现GPT-4o和Deepseek-R1表现优异但仍有改进空间。 large language model chain-of-thought
12 What Factors Affect LLMs and RLLMs in Financial Question Answering? 探究影响LLMs和RLLMs在金融问答中表现的关键因素 large language model chain-of-thought
13 KV Cache Steering for Controlling Frozen LLMs 提出KV缓存引导方法，无需微调即可控制冻结LLM的推理行为 chain-of-thought
14 From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation 构建专业级韩语评测基准KMMLU-Pro，提升LLM在行业知识领域的评估能力 large language model
15 Knowledge Fusion via Bidirectional Information Aggregation 提出KGA框架，通过双向信息聚合在推理时动态融合知识图谱增强LLM。 large language model
16 KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment KELPS：一种基于语义-句法对齐的可验证多语言自动形式化框架 large language model
17 Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing 提出拟人化不确定性，提升语言模型不确定性表达的真实性和可信度 large language model
18 AutoRAG-LoRA: Hallucination-Triggered Knowledge Retuning via Lightweight Adapters AutoRAG-LoRA：通过轻量级适配器实现幻觉触发的知识重调 large language model
19 A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations 提出基于提示的自然语言解释分类法以增强AI透明性 large language model
20 ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains ChainEdit：通过逻辑规则引导的链式传播，增强LLM知识编辑中的一致性 large language model
21 Can LLMs Reliably Simulate Real Students' Abilities in Mathematics and Reading Comprehension? 利用大规模语言模型模拟学生能力，评估其在智能辅导系统中的可靠性 large language model
22 Self-Improving Model Steering 提出SIMS：一种自提升模型引导框架，无需外部监督即可动态调整LLM。 large language model
23 Semantic-Augmented Latent Topic Modeling with LLM-in-the-Loop 提出LLM辅助的LDA主题模型，用于初始化和后校正，提升主题一致性。 large language model
24 A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench 提出clembench，一个基于对话游戏的LLM评估框架，易于扩展和复用。 large language model
25 Exploring Design of Multi-Agent LLM Dialogues for Research Ideation 探索多智能体LLM对话设计，用于科研创意生成 large language model ✅
26 CRMAgent: A Multi-Agent LLM System for E-Commerce CRM Message Template Generation CRMAgent：一种用于电商CRM消息模板生成的多Agent LLM系统 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🔗⭐
27 Distillation versus Contrastive Learning: How to Train Your Rerankers 对比学习与知识蒸馏：用于训练文本重排序器的有效策略研究 contrastive learning distillation
28 KAT-V1: Kwai-AutoThink Technical Report 提出 AutoThink 框架 KAT-V1，解决推理密集型任务中的过度思考问题。 reinforcement learning distillation large language model
29 OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique OpenCodeReasoning-II：通过自批判的简单测试时缩放方法提升代码生成 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页