cs.CL（2025-01-10）

📊 共 20 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) (19 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models	提出Migician，实现多模态大语言模型中自由形式的多图像精准定位。	large language model multimodal instruction following	✅
2	MinMo: A Multimodal Large Language Model for Seamless Voice Interaction	MinMo：用于无缝语音交互的多模态大型语言模型	large language model multimodal instruction following	✅
3	Cascaded Self-Evaluation Augmented Training for Lightweight Multimodal LLMs	提出级联自评估增强训练Cas-SEAT，提升轻量级多模态LLM的推理和自评估能力	large language model multimodal chain-of-thought
4	Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks	Bactrainus：优化大型语言模型以解决多跳复杂问答任务	large language model chain-of-thought
5	Self-Evolving Critique Abilities in Large Language Models	提出SCRIT框架，利用自生成数据提升大语言模型的自进化评判能力	large language model
6	Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts	提出MOBERT模型，通过中性化性别代词以减少医学领域LLM的性别偏见。	large language model
7	Iconicity in Large Language Models	研究表明大型语言模型能有效编码词汇象征性，甚至优于人类	large language model
8	Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages	大型语言模型在不同语系语言间共享潜在语法概念的表征	large language model
9	Environmental large language model Evaluation (ELLE) dataset: A Benchmark for Evaluating Generative AI applications in Eco-environment Domain	提出ELLE数据集，用于评估生成式AI在生态环境领域的应用能力	large language model	✅
10	Controlling Large Language Models Through Concept Activation Vectors	提出GCAV，通过概念激活向量实现对大语言模型生成内容细粒度控制	large language model
11	Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding	Fleurs-SLU：一个大规模多语种口语理解评测基准	large language model multimodal
12	Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains	提出多智能体微调方法，通过多样化推理链实现LLM的自主改进。	large language model
13	Effective faking of verbal deception detection with target-aligned adversarial attacks	利用目标对齐对抗攻击有效伪造言语欺骗检测	large language model
14	Affordably Fine-tuned LLMs Provide Better Answers to Course-specific MCQs	通过低成本微调的大语言模型能更好地回答课程相关的选择题	large language model
15	How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond	综述人机协同在自然语言处理中的应用，分析原则、形式化方法与未来挑战	large language model
16	Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea	以朝鲜为案例，揭示多语言LLM在信息幻觉上的视角差异	large language model
17	LLMs Reproduce Stereotypes of Sexual and Gender Minorities	揭示大型语言模型对性少数群体和性别少数群体的刻板印象再现	large language model
18	ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability	提出ConSim框架，利用LLM自动评估基于概念的解释方法有效性	large language model	✅
19	Multi-Step Reasoning in Korean and the Emergent Mirage	提出HRMCR基准以评估韩语多步推理能力	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction	评估大语言模型在未来事件预测中的可靠性，揭示其潜力和局限	predictive model large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页