cs.CL（2025-08-24）

📊 共 16 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) (10 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Are You Sure You're Positive? Consolidating Chain-of-Thought Agents with Uncertainty Quantification for Aspect-Category Sentiment Analysis 提出链式思维代理的不确定性量化以解决情感分析问题 large language model chain-of-thought
2 Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? 提出多代理辩论与投票机制以优化大语言模型决策 large language model ✅
3 DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards 提出DashboardQA以解决交互式仪表板问答评估问题 multimodal ✅
4 From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users 评估大型语言模型作为自主代理和工具用户的能力 large language model
5 Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies 提出多种模型适应策略以提升认知筛查的准确性 large language model multimodal
6 DropLoRA: Sparse Low-Rank Adaptation for Parameter-Efficient Fine-Tuning 提出DropLoRA以解决低秩适应方法性能不足问题 large language model instruction following ✅
7 UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat 评估ALLaM 34B以解决阿拉伯语LLM的文化和语言挑战 large language model
8 Capturing Legal Reasoning Paths from Facts to Law in Court Judgments using Knowledge Graphs 构建法律知识图谱以解决法律推理路径捕捉问题 large language model
9 CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation 提出CultranAI以增强阿拉伯文化知识表示 large language model
10 ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation 构建ClaimGen-CN数据集以促进法律索赔生成研究 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
11 Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models 提出以对齐为中心的范式以优化大语言模型的指令调优 distillation large language model multimodal
12 Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation 提出RouteDK框架以解决大语言模型知识蒸馏冲突问题 distillation large language model
13 SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation 提出自监督信度优化方法以解决检索增强生成中的信度问题 DPO direct preference optimization large language model ✅
14 CORE-RAG: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning 提出CORE以解决RAG文档压缩效率低下问题 reinforcement learning large language model
15 Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD 提出DuET-PD框架以解决LLMs在说服对话中的鲁棒性与适应性问题 DPO large language model ✅
16 LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions 提出KAIROS基准以解决LLMs在多智能体社交互动中的脆弱性问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页