cs.CL（2025-04-02）

📊 共 31 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) (24 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models 提出跨语言一致性框架，提升大语言模型在复杂推理任务中的性能 large language model chain-of-thought
2 A thorough benchmark of automatic text classification: From traditional approaches to large language models 自动文本分类基准测试：从传统方法到大型语言模型 large language model
3 OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models OpenThaiGPT 1.6和R1：以泰语为中心的开源推理大型语言模型 large language model
4 A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek OpenFOAMGPT结合大语言模型，探索低成本CFD自动化方案 large language model
5 Chain of Correction for Full-text Speech Recognition with Large Language Models 提出链式纠错（CoC）方法，利用大语言模型提升全文语音识别的纠错能力 large language model
6 SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models SemEval-2025 Task 4 旨在评估和提升大型语言模型中敏感内容不可学习的能力。 large language model
7 Urban Computing in the Era of Large Language Models 探索LLM在城市计算中的应用，提升决策能力与公众参与度 large language model
8 Better Bill GPT: Comparing Large Language Models against Legal Invoice Reviewers 首个实证研究：大型语言模型在法律发票审核中全面超越人类专家 large language model
9 Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language Understanding 提出英语枢轴CoT训练，解决极低资源语言的推理迁移问题 large language model chain-of-thought
10 One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image 揭示视觉文档RAG易受投毒攻击的脆弱性：单张恶意图片即可破坏检索与生成。 large language model
11 Subasa - Adapting Language Models for Low-resourced Offensive Language Detection in Sinhala Subasa：为僧伽罗语低资源环境下的冒犯性语言检测微调语言模型 large language model
12 A Practical Synthesis of Detecting AI-Generated Textual, Visual, and Audio Content 综述AI生成文本、图像和音频内容检测的实用方法，应对虚假信息等风险。 large language model
13 LRAGE: Legal Retrieval Augmented Generation Evaluation Tool LRAGE：法律领域检索增强生成系统评测开源工具 large language model ✅
14 YourBench: Easy Custom Evaluation Sets for Everyone YourBench：一种易于使用的自定义评估集生成框架，解决LLM评估难题 large language model
15 Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training 研究并扩展代码切换以提升多语言模型预训练效果 large language model
16 InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation InfiniteICL：通过长短期记忆转换突破上下文窗口大小限制 large language model
17 Testing Low-Resource Language Support in LLMs Using Language Proficiency Exams: the Case of Luxembourgish 利用语言能力考试评估LLM对低资源语言的支持：以卢森堡语为例 large language model
18 Register Always Matters: Analysis of LLM Pretraining Data Through the Lens of Language Variation 通过语域视角分析LLM预训练数据，揭示语域对模型性能的关键影响 large language model
19 PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation PROPHET：一个基于因果干预似然估计的可推断未来预测基准 large language model
20 Refining Interactions: Enhancing Anisotropy in Graph Neural Networks with Language Semantics 提出LanSAGNN，利用语言语义增强图神经网络的各向异性，提升文本属性图处理能力 large language model
21 FAIRE: Assessing Racial and Gender Bias in AI-Driven Resume Evaluations FAIRE：评估AI驱动简历评估中种族和性别偏见的基准测试 large language model ✅
22 ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning ToolACE-R：面向工具学习的模型感知迭代训练与自适应精炼框架 large language model
23 Adaptive Rectification Sampling for Test-Time Compute Scaling 提出自适应修正采样(AR-Sampling)，提升LLM在推理任务中的细粒度纠错能力。 large language model
24 Revisiting Funnel Transformers for Modern LLM Architectures with Comprehensive Ablations in Training and Inference Configurations 重新审视Funnel Transformer在现代LLM架构中的应用，并进行全面的训练和推理配置消融研究。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
25 DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models DiaTool-DPO：用于工具增强大语言模型的多轮直接偏好优化 DPO direct preference optimization large language model
26 Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation 综述：利用大型语言模型弥合机器翻译的语言鸿沟 reinforcement learning RLHF large language model
27 ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning ThinkPrune：通过强化学习剪枝LLM的长链式思考过程 reinforcement learning chain-of-thought ✅
28 OpenCodeReasoning: Advancing Data Distillation for Competitive Coding OpenCodeReasoning：通过数据蒸馏提升竞争性编程能力 reinforcement learning distillation large language model
29 OnRL-RAG: Real-Time Personalized Mental Health Dialogue System 提出OnRL-RAG，用于实时个性化心理健康对话系统，提升LLM在动态环境中的适应性。 reinforcement learning RLHF large language model
30 LL4G: Self-Supervised Dynamic Optimization for Graph-Based Personality Detection LL4G：基于图的性格检测的自监督动态优化框架 contrastive learning large language model
31 Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models? 揭示心智理论基准测试中，大语言模型可能无需显式人类式推理即可成功 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页