cs.CL(2025-08-18)

📊 共 28 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (22 🔗4) 支柱二:RL算法与架构 (RL & Architecture) (6)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗
1 Enhancing Cryptocurrency Sentiment Analysis with Multimodal Features 提出多模态特征增强加密货币情感分析方法 large language model multimodal
2 LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models 提出LinguaSafe以解决多语言安全评估不足问题 large language model
3 Leveraging Large Language Models for Predictive Analysis of Human Misery 利用大型语言模型预测人类痛苦评分 large language model
4 Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation 提出信号与噪声框架以降低语言模型评估的不确定性 large language model
5 Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis 提出Datarus-R1以解决自动化数据分析中的推理问题 chain-of-thought
6 Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs 系统审计残疾条件下的LLMs偏见问题 large language model
7 DAIQ: Auditing Demographic Attribute Inference from Question in LLMs 提出DAIQ框架以审计LLMs中的人口属性推断问题 large language model
8 RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns 提出RepreGuard以解决LLM生成文本检测的鲁棒性问题 large language model
9 Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries 提出BlindSpot框架以识别和量化联络中心摘要中的操作偏见 large language model
10 A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models 提出主动自我精炼方法以提升语言模型输出质量 large language model
11 AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation 提出AutoBnB-RAG以增强多智能体事件响应能力 large language model
12 All for law and law for all: Adaptive RAG Pipeline for Legal Research 提出自适应RAG管道以提升法律研究效率 large language model
13 Doğal Dil İşlemede Tokenizasyon Standartları ve Ölçümü: Türkçe Üzerinden Büyük Dil Modellerinin Karşılaştırmalı Analizi 提出针对土耳其语的分词标准以解决语言模型性能问题 large language model
14 Büyük Dil Modelleri için TR-MMLU Benchmarkı: Performans Değerlendirmesi, Zorluklar ve İyileştirme Fırsatları 提出TR-MMLU基准以评估土耳其语大型语言模型的能力 large language model
15 Analyzing Information Sharing and Coordination in Multi-Agent Planning 构建LLM基础的MAS以解决复杂旅行规划问题 large language model
16 When Alignment Hurts: Decoupling Representational Spaces in Multilingual Models 提出在线变分探测框架以解决多语言模型的表示空间解耦问题 large language model
17 CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description 提出CRED-SQL以解决大规模数据库文本到SQL解析中的语义不匹配问题 large language model
18 DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning 提出DESIGNER以解决多学科推理数据合成问题 large language model
19 ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction 提出ToolACE-MT以解决多轮交互中的数据生成问题 large language model
20 Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing 提出Avengers-Pro以优化大语言模型的性能与效率 large language model
21 Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context 提出语义锚定以解决对话记忆持久性问题 large language model
22 CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features 提出CorrSteer以解决稀疏自编码器特征选择问题 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🔗
23 Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction 提出多LoRA交互的蒸馏方法以提升小模型数学推理能力 distillation large language model chain-of-thought
24 Beyond Modality Limitations: A Unified MLLM Approach to Automated Speaking Assessment with Effective Curriculum Learning 提出统一的多模态大语言模型以解决自动口语评估中的模态限制问题 curriculum learning large language model multimodal
25 Stands to Reason: Investigating the Effect of Reasoning on Idiomaticity Detection 探讨推理能力对习语检测的影响 distillation large language model chain-of-thought
26 Improving Detection of Watermarked Language Models 提出混合检测方法以提升水印语言模型的检测能力 reinforcement learning RLHF large language model
27 Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward 提出Atom-Searcher以解决复杂任务中的推理与搜索问题 reinforcement learning large language model
28 Insight Rumors: A Novel Textual Rumor Locating and Marking Model Leveraging Att_BiMamba2 Network 提出Insight Rumors以解决文本谣言定位与标记问题 Mamba

⬅️ 返回 cs.CL 首页 · 🏠 返回主页