cs.CL（2025-06-26）

📊 共 31 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (24 🔗4) 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 Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents 提出Agent-RewardBench以解决多模态智能体奖励建模问题 large language model multimodal
2 Towards Transparent AI: A Survey on Explainable Large Language Models 综述可解释大型语言模型的研究进展与挑战 large language model
3 Evaluating List Construction and Temporal Understanding capabilities of Large Language Models 提出TLQA基准以解决大语言模型的时间理解与列表构建问题 large language model ✅
4 Potemkin Understanding in Large Language Models 提出形式框架以评估大型语言模型的理解能力 large language model
5 Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation 提出Refined Graph-based RAG以解决弱检索器与大语言模型对齐问题 large language model
6 Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis 应用综合信息理论分析大语言模型的意识表现 large language model
7 Large Language Models Acing Chartered Accountancy 提出CA-Ben基准以评估大型语言模型在会计领域的能力 large language model
8 Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models 提出ProCI框架以解决隐性混淆问题 large language model
9 Structuralist Approach to AI Literary Criticism: Leveraging Greimas Semiotic Square for Large Language Models 提出GLASS框架以提升LLM的文学批评能力 large language model
10 Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval 提出基于句法检索的提示策略以增强自动术语提取 large language model
11 Theory of Mind in Action: The Instruction Inference Task 提出Instruction Inference任务以评估代理的心智理论能力 large language model chain-of-thought
12 Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation 提出Omni-RAG以解决复杂用户查询处理问题 large language model chain-of-thought
13 Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models 提出文本自回归模型以解决视觉对话中的指称表达检测问题 large language model multimodal
14 Small Encoders Can Rival Large Decoders in Detecting Groundedness 提出轻量级编码器以解决大型解码器在基础性检测中的不足 large language model ✅
15 Exploring the Structure of AI-Induced Language Change in Scientific English 探讨AI引发的科学英语语言结构变化 large language model
16 Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection 提出领域知识增强的LLM框架以解决欺诈和概念漂移检测问题 large language model
17 Exploring the change in scientific readability following the release of ChatGPT 分析ChatGPT发布后科学论文可读性变化 large language model
18 (Fact) Check Your Bias 研究语言模型偏见对事实核查结果的影响 large language model ✅
19 Text2Cypher Across Languages: Evaluating and Finetuning LLMs 提出多语言Text2Cypher评估与微调方法以提升数据库查询生成 large language model
20 Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning 提出Double-Checker以增强慢思维LLMs的推理能力 large language model ✅
21 Cat and Mouse -- Can Fake Text Generation Outpace Detector Systems? 探讨假文本生成与检测系统的博弈关系 large language model
22 Prompt-Guided Turn-Taking Prediction 提出基于文本提示的动态轮流预测模型以改善对话系统 large language model
23 MT2-CSD: A New Dataset and Multi-Semantic Knowledge Fusion Method for Conversational Stance Detection 提出MT2-CSD数据集与LLM-CRAN方法以解决对话立场检测问题 large language model
24 FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language 提出FineWeb2以解决多语言预训练数据处理问题 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 DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning 提出DALR以解决多模态句子表示学习中的对齐问题 representation learning distillation multimodal
26 Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning 提出MDGCL以解决多领域图对比学习问题 contrastive learning foundation model
27 AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text 提出AgentStealth以解决用户生成文本匿名化问题 reinforcement learning contrastive learning large language model ✅
28 Bridging Offline and Online Reinforcement Learning for LLMs 提出强化学习方法以优化大语言模型的在线与离线训练 reinforcement learning direct preference optimization large language model
29 SAC: A Framework for Measuring and Inducing Personality Traits in LLMs with Dynamic Intensity Control 提出SAC框架以动态控制LLM个性特征的强度 SAC large language model
30 KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model 提出KaLM-Embedding-V2以提升文本嵌入模型性能 representation learning distillation large language model
31 Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments 通过交互式LLM对齐提升社会驱动对话中的用户参与度 DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页